format-version: 1.2 data-version: releases/2024-06-26 subsetdef: https://w3id.org/aio/BiasSubset "Bias Subset" subsetdef: https://w3id.org/aio/ClassSubset "Class Subset" subsetdef: https://w3id.org/aio/FunctionSubset "Function Subset" subsetdef: https://w3id.org/aio/LayerSubset "Layer Subset" subsetdef: https://w3id.org/aio/MachineLearningSubset "Machine Learning Subset" subsetdef: https://w3id.org/aio/ModelSubset "Model Subset" subsetdef: https://w3id.org/aio/NetworkSubset "Network Subset" subsetdef: https://w3id.org/aio/PreprocessingSubset "Preprocessing Subset" ontology: aio property_value: http://purl.org/dc/terms/description "This ontology models classes and relationships describing deep learning networks, their component layers and activation functions, as well as potential biases." xsd:string property_value: http://purl.org/dc/terms/license http://creativecommons.org/licenses/by/4.0/ property_value: http://purl.org/dc/terms/title "Artificial Intelligence Ontology" xsd:string property_value: owl:versionInfo "2024-06-26" xsd:string [Term] id: https://w3id.org/aio/AbstractRNNCell name: AbstractRNNCell def: "An abstract layer object representing an RNN cell that is the base class for implementing RNN cells with custom behavior." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/AbstractRNNCell] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/ActivationLayer name: Activation Layer def: "A layer that applies an activation function to an output." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Activation] comment: Applies an activation function to an output. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/ActiveLearning name: Active Learning def: "A type of machine learning focused on methods that interactively query a user or another information source to label new data points with the desired outputs." [https://en.wikipedia.org/wiki/Active_learning_(machine_learning)] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Query Learning" EXACT [] is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/ActivityBias name: Activity Bias def: "A use and interpretation bias occurring when systems/platforms get training data from their most active users rather than less active or inactive users." [https://en.wikipedia.org/wiki/Interpretive_bias] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/UseAndInterpretationBias ! Use And Interpretation Bias [Term] id: https://w3id.org/aio/ActivityRegularizationLayer name: ActivityRegularization Layer def: "A regularization layer that applies an update to the cost function based on input activity." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ActivityRegularization] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RegularizationLayer ! Regularization Layer [Term] id: https://w3id.org/aio/AdaptiveAvgPool1DLayer name: AdaptiveAvgPool1D Layer def: "A pooling layer that applies a 1D adaptive average pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AdaptiveAvgPool1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AdaptiveAvgPool2DLayer name: AdaptiveAvgPool2D Layer def: "A pooling layer that applies a 2D adaptive average pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AdaptiveAvgPool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AdaptiveAvgPool3DLayer name: AdaptiveAvgPool3D Layer def: "A pooling layer that applies a 3D adaptive average pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AdaptiveAvgPool3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AdaptiveMaxPool1DLayer name: AdaptiveMaxPool1D Layer def: "A pooling layer that applies a 1D adaptive max pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AdaptiveMaxPool1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AdaptiveMaxPool2DLayer name: AdaptiveMaxPool2D Layer def: "A pooling layer that applies a 2D adaptive max pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AdaptiveMaxPool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AdaptiveMaxPool3DLayer name: AdaptiveMaxPool3D Layer def: "A pooling layer that applies a 3D adaptive max pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AdaptiveMaxPool3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AddLayer name: Add Layer def: "A merging layer that adds a list of inputs taking as input a list of tensors all of the same shape." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Add] comment: Layer that adds a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/MergingLayer ! Merging Layer [Term] id: https://w3id.org/aio/AdditionLayer name: Addition Layer def: "A layer that adds inputs from one or more other layers to cells or neurons of a target layer." [] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/AdditiveAttentionLayer name: AdditiveAttention Layer def: "An attention layer that implements additive attention also known as Bahdanau-style attention." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdditiveAttention] comment: Additive attention layer, a.k.a. Bahdanau-style attention. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/AttentionLayer ! Attention Layer [Term] id: https://w3id.org/aio/AlphaDropoutLayer name: AlphaDropout Layer def: "A regularization layer that applies Alpha Dropout to the input keeping mean and variance of inputs to ensure self-normalizing property." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/AlphaDropout] comment: Applies Alpha Dropout to the input. Alpha Dropout is a Dropout that keeps mean and variance of inputs to their original values, in order to ensure the self-normalizing property even after this dropout. Alpha Dropout fits well to Scaled Exponential Linear Units by randomly setting activations to the negative saturation value. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RegularizationLayer ! Regularization Layer [Term] id: https://w3id.org/aio/AmplificationBias name: Amplification Bias def: "A processing bias arising when the distribution over prediction outputs is skewed compared to the prior distribution of the prediction target." [https://royalsocietypublishing.org/doi/10.1098/rspb.2019.0165#d1e5237] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/ProcessingBias ! Processing Bias [Term] id: https://w3id.org/aio/AnchoringBias name: Anchoring Bias def: "A cognitive bias characterized by the influence of a reference point or anchor on decisions leading to insufficient adjustment from that anchor point." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/AnnotatorReportingBias name: Annotator Reporting Bias def: "An individual bias occurring when users rely on automation as a heuristic replacement for their own information seeking and processing." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/ArtificialNeuralNetwork name: Artificial Neural Network def: "A network based on a collection of connected units called artificial neurons modeled after biological neurons." [https://en.wikipedia.org/wiki/Artificial_neural_network] comment: An artificial neural network (ANN) is based on a collection of connected units or nodes called artificial neurons, modeled after biological neurons, with connections transmitting signals processed by non-linear functions. subset: https://w3id.org/aio/NetworkSubset synonym: "ANN" EXACT [] synonym: "NN" EXACT [] is_a: https://w3id.org/aio/Network ! Network [Term] id: https://w3id.org/aio/AssociationRuleLearning name: Association Rule Learning def: "A supervised learning method focused on a rule-based approach for discovering interesting relations between variables in large databases." [https://en.wikipedia.org/wiki/Association_rule_learning] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/SupervisedLearning ! Supervised Learning [Term] id: https://w3id.org/aio/AttentionLayer name: Attention Layer def: "A layer that implements dot-product attention also known as Luong-style attention." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Attention] comment: Dot-product attention layer, a.k.a. Luong-style attention. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/AutoEncoderNetwork name: Auto Encoder Network def: "An unsupervised pretrained network that learns efficient codings of unlabeled data by training to ignore insignificant data and regenerate input from encoding." [https://en.wikipedia.org/wiki/Autoencoder] comment: Layers: Input, Hidden, Matched Output-Input subset: https://w3id.org/aio/NetworkSubset synonym: "AE" EXACT [] is_a: https://w3id.org/aio/UnsupervisedPretrainedNetwork ! Unsupervised Pretrained Network relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/MatchedInputOutputLayer ! has part Matched Input-Output Layer [Term] id: https://w3id.org/aio/AutomationComplacencyBias name: Automation Complacency Bias def: "A bias characterized by over-reliance on automated systems leading to attenuated human skills." [https://doi.org/10.6028/NIST.SP.1270] comment: Over-reliance on automated systems, leading to attenuated human skills, such as with spelling and autocorrect. subset: https://w3id.org/aio/BiasSubset synonym: "Automation Complaceny" EXACT [] is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/AutoregressiveConditionalHeteroskedasticity name: Autoregressive Conditional Heteroskedasticity def: "A model that describes the variance of the current error term as a function of the previous periods' error terms, capturing volatility clustering. Used for time series data." [] subset: https://w3id.org/aio/ModelSubset synonym: "ARCH" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/AutoregressiveDistributedLag name: Autoregressive Distributed Lag def: "A model that includes lagged values of both the dependent variable and one or more independent variables, capturing dynamic relationships over time. Used in time series analysis." [] subset: https://w3id.org/aio/ModelSubset synonym: "ARDL" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/AutoregressiveIntegratedMovingAverage name: Autoregressive Integrated Moving Average def: "A model which combines autoregression (AR), differencing (I), and moving average (MA) components. Used for analyzing and forecasting time series data." [] subset: https://w3id.org/aio/ModelSubset synonym: "ARIMA" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/AutoregressiveLanguageModel name: Autoregressive Language Model def: "A language model that generates text sequentially predicting one token at a time based on the previously generated tokens excelling at natural language generation tasks by modeling the probability distribution over sequences of tokens." [] subset: https://w3id.org/aio/ModelSubset synonym: "generative language model" RELATED [] synonym: "sequence-to-sequence model" RELATED [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/AutoregressiveMovingAverage name: Autoregressive Moving Average def: "A model that combines autoregressive (AR) and moving average (MA) components to represent time series data, suitable for stationary series without the need for differencing." [] subset: https://w3id.org/aio/ModelSubset synonym: "ARMA" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/AvailabilityHeuristicBias name: Availability Heuristic Bias def: "A cognitive bias characterized by a mental shortcut where easily recalled information is overweighted in judgment and decision-making." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Availability Bias" EXACT [] synonym: "Availability Heuristic" EXACT [] is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/AverageLayer name: Average Layer def: "A merging layer that averages a list of inputs element-wise taking as input a list of tensors all of the same shape." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Average] comment: Layer that averages a list of inputs element-wise. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/MergingLayer ! Merging Layer [Term] id: https://w3id.org/aio/AveragePooling1DLayer name: AveragePooling1D Layer def: "A pooling layer that performs average pooling for temporal data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling1D] comment: Average pooling for temporal data. Downsamples the input representation by taking the average value over the window defined by pool_size. The window is shifted by strides. The resulting output when using "valid" padding option has a shape of: output_shape = (input_shape - pool_size + 1) / strides). The resulting output shape when using the "same" padding option is: output_shape = input_shape / strides. subset: https://w3id.org/aio/LayerSubset synonym: "AvgPool1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AveragePooling2DLayer name: AveragePooling2D Layer def: "A pooling layer that performs average pooling for spatial data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling2D] comment: Average pooling operation for spatial data. Downsamples the input along its spatial dimensions (height and width) by taking the average value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension. The resulting output when using "valid" padding option has a shape (number of rows or columns) of: output_shape = math.floor((input_shape - pool_size) / strides) + 1 (when input_shape >= pool_size). The resulting output shape when using the "same" padding option is: output_shape = math.floor((input_shape - 1) / strides) + 1. subset: https://w3id.org/aio/LayerSubset synonym: "AvgPool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AveragePooling3DLayer name: AveragePooling3D Layer def: "A pooling layer that performs average pooling for 3D data (spatial or spatio-temporal)." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling3D] comment: Average pooling operation for 3D data (spatial or spatio-temporal). Downsamples the input along its spatial dimensions (depth, height, and width) by taking the average value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension. subset: https://w3id.org/aio/LayerSubset synonym: "AvgPool3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AvgPool1DLayer name: AvgPool1D Layer def: "A pooling layer that applies a 1D average pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AvgPool1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AvgPool2DLayer name: AvgPool2D Layer def: "A pooling layer that applies a 2D average pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AvgPool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/AvgPool3DLayer name: AvgPool3D Layer def: "A pooling layer that applies a 3D average pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "AvgPool3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/BackfedInputLayer name: Backfed Input Layer def: "An input layer that receives values from another layer." [] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/InputLayer ! Input Layer [Term] id: https://w3id.org/aio/BatchNorm1DLayer name: BatchNorm1D Layer def: "A batch normalization layer that applies Batch Normalization over a 2D or 3D input." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Batch Normalization over a 2D or 3D input as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift . subset: https://w3id.org/aio/LayerSubset synonym: "BatchNorm1D" EXACT [] is_a: https://w3id.org/aio/BatchNormalizationLayer ! BatchNormalization Layer [Term] id: https://w3id.org/aio/BatchNorm2DLayer name: BatchNorm2D Layer def: "A batch normalization layer that applies Batch Normalization over a 4D input." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Batch Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift . subset: https://w3id.org/aio/LayerSubset synonym: "BatchNorm2D" EXACT [] is_a: https://w3id.org/aio/BatchNormalizationLayer ! BatchNormalization Layer [Term] id: https://w3id.org/aio/BatchNorm3DLayer name: BatchNorm3D Layer def: "A batch normalization layer that applies Batch Normalization over a 5D input." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Batch Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift . subset: https://w3id.org/aio/LayerSubset synonym: "BatchNorm3D" EXACT [] is_a: https://w3id.org/aio/BatchNormalizationLayer ! BatchNormalization Layer [Term] id: https://w3id.org/aio/BatchNormalizationLayer name: BatchNormalization Layer def: "A normalization layer that normalizes its inputs applying a transformation that maintains the mean close to 0 and the standard deviation close to 1." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/BatchNormalization] comment: Layer that normalizes its inputs. Batch normalization applies a transformation that maintains the mean output close to 0 and the output standard deviation close to 1. Importantly, batch normalization works differently during training and during inference. During training (i.e. when using fit() or when calling the layer/model with the argument training=True), the layer normalizes its output using the mean and standard deviation of the current batch of inputs. That is to say, for each channel being normalized, the layer returns gamma * (batch - mean(batch)) / sqrt(var(batch) + epsilon) + beta, where: epsilon is small constant (configurable as part of the constructor arguments), gamma is a learned scaling factor (initialized as 1), which can be disabled by passing scale=False to the constructor. beta is a learned offset factor (initialized as 0), which can be disabled by passing center=False to the constructor. During inference (i.e. when using evaluate() or predict() or when calling the layer/model with the argument training=False (which is the default), the layer normalizes its output using a moving average of the mean and standard deviation of the batches it has seen during training. That is to say, it returns gamma * (batch - self.moving_mean) / sqrt(self.moving_var + epsilon) + beta. self.moving_mean and self.moving_var are non-trainable variables that are updated each time the layer in called in training mode, as such: moving_mean = moving_mean * momentum + mean(batch) * (1 - momentum) moving_var = moving_var * momentum + var(batch) * (1 - momentum). subset: https://w3id.org/aio/LayerSubset synonym: "BatchNorm" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/BayesianNetwork name: Bayesian Network def: "A network that is a probabilistic graphical model representing variables and their conditional dependencies via a directed acyclic graph." [https://en.wikipedia.org/wiki/Bayesian_network] subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/Network ! Network [Term] id: https://w3id.org/aio/BehavioralBias name: Behavioral Bias def: "An individual bias characterized by systematic distortions in user behavior across platforms or contexts or across users represented in different datasets." [https://doi.org/10.6028/NIST.SP.1270] comment: Systematic distortions in user behavior across platforms or contexts, or across users represented in different datasets. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/Bias name: Bias def: "A systematic error introduced into sampling or testing by selecting or encouraging one outcome or answer over others." [https://www.merriam-webster.com/dictionary/bias] subset: https://w3id.org/aio/BiasSubset [Term] id: https://w3id.org/aio/Biclustering name: Biclustering def: "A machine learning task focused on methods that simultaneously cluster the rows and columns of a matrix to identify submatrices with coherent patterns." [https://en.wikipedia.org/wiki/Biclustering] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Block Clustering" EXACT [] synonym: "Co-clustering" EXACT [] synonym: "Joint Clustering" EXACT [] synonym: "Two-mode Clustering" EXACT [] synonym: "Two-way Clustering" EXACT [] is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/BidirectionalLayer name: Bidirectional Layer def: "A recurrent layer that is a bidirectional wrapper for RNNs." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Bidirectional] comment: Bidirectional wrapper for RNNs. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RecurrentLayer ! Recurrent Layer [Term] id: https://w3id.org/aio/BidirectionalTransformerLanguageModel name: Bidirectional Transformer Language Model def: "A transformer language model such as BERT that uses the transformer architecture to build deep bidirectional representations by predicting masked tokens based on their context." [https://arxiv.org/abs/1810.04805, https://en.wikipedia.org/wiki/BERT_(language_model)] subset: https://w3id.org/aio/ModelSubset synonym: "BERT" EXACT [] synonym: "Bidirectional Transformer LM" EXACT [] is_a: https://w3id.org/aio/TransformerLanguageModel ! Transformer Language Model [Term] id: https://w3id.org/aio/BinaryClassification name: Binary Classification def: "A machine learning task focused on methods that classify elements into two groups based on a classification rule." [https://en.wikipedia.org/wiki/Binary_classification] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/Classification ! Classification [Term] id: https://w3id.org/aio/BoltzmannMachineNetwork name: Boltzmann Machine Network def: "A symmetrically connected network that is a type of stochastic recurrent neural network and Markov random field." [https://en.wikipedia.org/wiki/Boltzmann_machine] comment: Layers: Backfed Input, Probabilistic Hidden subset: https://w3id.org/aio/NetworkSubset synonym: "BM" EXACT [] synonym: "Sherrington–Kirkpatrick model with external field" EXACT [] synonym: "stochastic Hopfield network with hidden units" EXACT [] synonym: "stochastic Ising-Lenz-Little model" EXACT [] is_a: https://w3id.org/aio/SymmetricallyConnectedNetwork ! Symmetrically Connected Network relationship: BFO:0000051 https://w3id.org/aio/BackfedInputLayer ! has part Backfed Input Layer relationship: BFO:0000051 https://w3id.org/aio/ProbabilisticHiddenLayer ! has part Probabilistic Hidden Layer [Term] id: https://w3id.org/aio/CategoricalFeaturesPreprocessingLayer name: Categorical Features Preprocessing Layer def: "A layer that performs categorical data preprocessing operations." [https://keras.io/guides/preprocessing_layers/] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/CategoryEncodingLayer name: CategoryEncoding Layer def: "A categorical features preprocessing layer that encodes integer features providing options for condensing data into a categorical encoding." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/CategoryEncoding] comment: A preprocessing layer which encodes integer features. This layer provides options for condensing data into a categorical encoding when the total number of tokens are known in advance. It accepts integer values as inputs, and it outputs a dense or sparse representation of those inputs. For integer inputs where the total number of tokens is not known, use tf.keras.layers.IntegerLookup instead. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/CategoricalFeaturesPreprocessingLayer ! Categorical Features Preprocessing Layer [Term] id: https://w3id.org/aio/CausalGraphicalModel name: Causal Graphical Model def: "A probabilistic graphical model used to encode assumptions about the data-generating process." [https://en.wikipedia.org/wiki/Causal_graph] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Casaul Bayesian Network" EXACT [] synonym: "Casaul Graph" EXACT [] synonym: "DAG" EXACT [] synonym: "Directed Acyclic Graph" EXACT [] synonym: "Path Diagram" EXACT [] is_a: https://w3id.org/aio/ProbabilisticGraphicalModel ! Probabilistic Graphical Model [Term] id: https://w3id.org/aio/CausalLLM name: Causal LLM def: "A large language model that only attends to previous tokens in the sequence when generating text modeling the probability distribution autoregressively from left-to-right or causally." [] subset: https://w3id.org/aio/ModelSubset synonym: "autoregressive" RELATED [] synonym: "Causal Large Language Model" EXACT [] synonym: "unidirectional" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/CenterCropLayer name: CenterCrop Layer def: "An image preprocessing layer that crops the central portion of images to a target size." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/CenterCrop] comment: A preprocessing layer which crops images. This layers crops the central portion of the images to a target size. If an image is smaller than the target size, it will be resized and cropped so as to return the largest possible window in the image that matches the target aspect ratio. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ImagePreprocessingLayer ! Image Preprocessing Layer [Term] id: https://w3id.org/aio/Classification name: Classification def: "A supervised learning task focused on methods that distinguish and distribute kinds of \"things\" into different groups." [https://en.wikipedia.org/wiki/Classification_(general_theory)] comment: Methods that distinguish and distribute kinds of "things" into different groups. subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/SupervisedLearning ! Supervised Learning [Term] id: https://w3id.org/aio/Cleaning name: Cleaning def: "The process of removing noise inconsistencies and irrelevant information from data to enhance its quality and prepare it for analysis or further processing." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Data cleaning" RELATED [] synonym: "Data Cleansing" EXACT [] synonym: "Standardization" EXACT [] synonym: "Text normalization" RELATED [] is_a: https://w3id.org/aio/DataPreparation ! Data Preparation [Term] id: https://w3id.org/aio/Clustering name: Clustering def: "A machine learning task focused on methods that group a set of objects such that objects in the same group are more similar to each other than to those in other groups." [https://en.wikipedia.org/wiki/Cluster_analysis] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Cluster analysis" EXACT [] is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/CognitiveBias name: Cognitive Bias def: "A systematic deviation from rational judgment and decision-making including adaptive mental shortcuts known as heuristics." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/CompositionalGeneralizationLLM name: Compositional Generalization LLM def: "A large language model that is trained to understand and recombine the underlying compositional structures in language enabling better generalization to novel combinations and out-of-distribution examples." [] subset: https://w3id.org/aio/ModelSubset synonym: "Compositional Generalization Large Language Model" EXACT [] synonym: "out-of-distribution generalization" RELATED [] synonym: "systematic generalization" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ComputationalBias name: Computational Bias def: "A bias caused by differences between results and facts in the process of data analysis (including the source of data the estimator chose) and analysis methods." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Statistical Bias" EXACT [] is_a: https://w3id.org/aio/Bias ! Bias [Term] id: https://w3id.org/aio/ConcatenateLayer name: Concatenate Layer def: "A merging layer that concatenates a list of inputs taking as input a list of tensors all of the same shape except for the concatenation axis." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Concatenate] comment: Layer that concatenates a list of inputs. It takes as input a list of tensors, all of the same shape except for the concatenation axis, and returns a single tensor that is the concatenation of all inputs. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/MergingLayer ! Merging Layer [Term] id: https://w3id.org/aio/ConceptDriftBias name: Concept Drift Bias def: "A use and interpretation bias due to the use of a system outside its planned domain of application causing performance gaps between laboratory settings and the real world." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Concept Drift" EXACT [] is_a: https://w3id.org/aio/UseAndInterpretationBias ! Use And Interpretation Bias [Term] id: https://w3id.org/aio/ConfirmationBias name: Confirmation Bias def: "A cognitive bias characterized by the tendency to prefer information that confirms existing beliefs influencing the search for interpretation of and recall of information." [https://doi.org/10.6028/NIST.SP.1270] comment: The tendency to prefer information that confirms existing beliefs, influencing the search for, interpretation of, and recall of information. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/ConsumerBias name: Consumer Bias def: "A bias arising when an algorithm or platform provides users a venue to express their biases occurring from either side in a digital interaction." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/ContentProductionBias name: Content Production Bias def: "A use and interpretation bias arising from structural lexical semantic and syntactic differences in user-generated content." [https://doi.org/10.6028/NIST.SP.1270] comment: Bias from structural, lexical, semantic, and syntactic differences in user-generated content. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/UseAndInterpretationBias ! Use And Interpretation Bias [Term] id: https://w3id.org/aio/ContinualLearning name: Continual Learning def: "A deep neural network that learns sequential tasks without forgetting knowledge from preceding tasks and without access to old task data during new task training." [https://paperswithcode.com/task/continual-learning] comment: Learning a model for sequential tasks without forgetting knowledge from preceding tasks, with no access to old task data during new task training. subset: https://w3id.org/aio/NetworkSubset synonym: "Incremental Learning" EXACT [] synonym: "Life-Long Learning" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/ContinualLearningLLM name: Continual Learning LLM def: "A large language model that continually acquires new knowledge and skills over time without forgetting previously learned information allowing the model to adapt and expand its capabilities as new data becomes available." [] subset: https://w3id.org/aio/ModelSubset synonym: "catastrophic forgetting" RELATED [] synonym: "CL-Large Language Model" EXACT [] synonym: "Continual Learning Large Language Model" EXACT [] synonym: "lifelong learning" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ContrastiveLearning name: Contrastive Learning def: "A deep neural network self-supervised learning approach that learns to distinguish between similar and dissimilar data samples." [https://arxiv.org/abs/2202.14037] comment: Contrastive learning is a self-supervised learning approach in which the model learns to distinguish between similar and dissimilar pairs of data samples. By maximizing the similarity between positive pairs (similar samples) and minimizing the similarity between negative pairs (dissimilar samples), the model learns to capture meaningful representations of the data. This method is particularly effective for representation learning and is widely used in tasks such as image classification, clustering, and retrieval. Contrastive learning techniques often employ loss functions such as the contrastive loss or the triplet loss to achieve these objectives. subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/ContrastiveLearningLLM name: Contrastive Learning LLM def: "A large language model that is trained to pull semantically similar samples closer together and push dissimilar samples apart in the representation space learning high-quality features useful for downstream tasks." [] subset: https://w3id.org/aio/ModelSubset synonym: "Representation learning" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ControllableLLM name: Controllable LLM def: "A large language model that allows for explicit control over certain attributes of the generated text such as style tone topic or other desired characteristics through conditioning or specialized training objectives." [] comment: A controllable LLM allows for explicit control over certain attributes of the generated text, such as style, tone, topic, or other desired characteristics, through conditioning or specialized training objectives. subset: https://w3id.org/aio/ModelSubset synonym: "conditional generation" RELATED [] synonym: "Controllable Large Language Model" EXACT [] synonym: "guided generation" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ConvLSTM1DLayer name: ConvLSTM1D Layer def: "A convolutional layer that implements a 1D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM1D] comment: 1D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/ConvLSTM2DLayer name: ConvLSTM2D Layer def: "A convolutional layer that implements a 2D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM2D] comment: 2D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/ConvLSTM3DLayer name: ConvLSTM3D Layer def: "A convolutional layer that implements a 3D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM3D] comment: 3D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/Convolution1DLayer name: Convolution1D Layer def: "A layer that implements 1D convolution (e.g. temporal convolution)." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1D] subset: https://w3id.org/aio/LayerSubset synonym: "Conv1D" EXACT [] synonym: "Conv1D Layer" EXACT [] synonym: "Convolution1D" EXACT [] synonym: "nn.Conv1D" EXACT [] is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/Convolution1DTransposeLayer name: Convolution1DTranspose Layer def: "A layer that implements transposed 1D convolution sometimes called deconvolution." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1DTranspose] comment: Transposed convolution layer (sometimes called Deconvolution). The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 3) for data with 128 time steps and 3 channels. subset: https://w3id.org/aio/LayerSubset synonym: "Conv1DTranspose Layer" EXACT [] synonym: "Convolution1DTranspose" EXACT [] synonym: "ConvTranspose1D" EXACT [] synonym: "nn.ConvTranspose1D" EXACT [] is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/Convolution2DLayer name: Convolution2D Layer def: "A layer that implements 2D convolution (e.g. spatial convolution over images)." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2D] comment: 2D convolution layer (e.g. spatial convolution over images). This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 3) for 128x128 RGB pictures in data_format="channels_last". You can use None when a dimension has variable size. subset: https://w3id.org/aio/LayerSubset synonym: "Conv2D" EXACT [] synonym: "Conv2D Layer" EXACT [] synonym: "Convolution2D" EXACT [] synonym: "nn.Conv2D" EXACT [] is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/Convolution2DTransposeLayer name: Convolution2DTranspose Layer def: "A layer that implements transposed 2D convolution" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2DTranspose] comment: Transposed convolution layer (sometimes called Deconvolution). subset: https://w3id.org/aio/LayerSubset synonym: "Conv2DTranspose Layer" EXACT [] synonym: "Convolution2DTranspose" EXACT [] synonym: "ConvTranspose2D" EXACT [] synonym: "nn.ConvTranspose2D" EXACT [] is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/Convolution3DLayer name: Convolution3D Layer def: "A layer that implements 3D convolution (e.g. spatial convolution over volumes)." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3D] comment: 3D convolution layer (e.g. spatial convolution over volumes). This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 128, 1) for 128x128x128 volumes with a single channel, in data_format="channels_last". subset: https://w3id.org/aio/LayerSubset synonym: "Conv3D" EXACT [] synonym: "Conv3D Layer" EXACT [] synonym: "Convolution3D" EXACT [] synonym: "nn.Conv3D" EXACT [] is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/Convolution3DTransposeLayer name: Convolution3DTranspose Layer def: "A layer that implements transposed 3D convolution" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3DTranspose] comment: Transposed convolution layer (sometimes called Deconvolution). The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 128, 3) for a 128x128x128 volume with 3 channels if data_format="channels_last". subset: https://w3id.org/aio/LayerSubset synonym: "Conv3DTranspose Layer" EXACT [] synonym: "Convolution3DTranspose" EXACT [] synonym: "ConvTranspose3D" EXACT [] synonym: "nn.ConvTranspose3D" EXACT [] is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/ConvolutionalLayer name: Convolutional Layer def: "A layer that contains a set of filters (or kernels) parameters of which are to be learned throughout the training." [https://www.sciencedirect.com/topics/engineering/convolutional-layer] comment: A convolutional layer is the main building block of a CNN. It contains a set of filters (or kernels), parameters of which are to be learned throughout the training. The size of the filters is usually smaller than the actual image. Each filter convolves with the image and creates an activation map. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/Cropping1DLayer name: Cropping1D Layer def: "A layer that crops along the time dimension (axis 1) for 1D input." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping1D] comment: Cropping layer for 1D input (e.g. temporal sequence). It crops along the time dimension (axis 1). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/Cropping2DLayer name: Cropping2D Layer def: "A layer that crops along spatial dimensions (i.e. height and width) for 2D input." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping2D] comment: Cropping layer for 2D input (e.g. picture). It crops along spatial dimensions, i.e. height and width. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/Cropping3DLayer name: Cropping3D Layer def: "A layer that crops along spatial dimensions (depth" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping3D] comment: Cropping layer for 3D data (e.g. spatial or spatio-temporal). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/CrossDomainLLM name: Cross-Domain LLM def: "A LLM that performs well across a wide range of domains without significant loss in performance, facilitated by advanced domain adaptation techniques." [] subset: https://w3id.org/aio/ModelSubset synonym: "cross-domain transfer" RELATED [] synonym: "domain adaptation" RELATED [] synonym: "Domain-General LLM" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/CurriculumLearning name: Curriculum Learning def: "A training strategy in machine learning where models are trained on data in a meaningful order starting with simpler examples and gradually increasing the complexity to improve learning efficiency and model performance." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Complexity grading" RELATED [] synonym: "Sequential Learning" EXACT [] synonym: "Sequential learning" RELATED [] synonym: "Structured Learning" EXACT [] is_a: https://w3id.org/aio/TrainingStrategies ! Training Strategies [Term] id: https://w3id.org/aio/CurriculumLearningLLM name: Curriculum Learning LLM def: "A large language model that is trained by presenting learning examples in a meaningful order from simple to complex mimicking the learning trajectory followed by humans." [] subset: https://w3id.org/aio/ModelSubset synonym: "Learning progression" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/DataAugmentation name: Data Augmentation def: "A technique used to increase the diversity and quantity of training data by applying various transformations such as rotation scaling flipping and cropping to existing data samples enhancing the robustness and performance of machine learning models." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Data Enrichment" EXACT [] synonym: "Data Expansion" EXACT [] synonym: "Paraphrasing" RELATED [] synonym: "Synonym replacement" RELATED [] is_a: https://w3id.org/aio/DataEnhancement ! DataEnhancement [Term] id: https://w3id.org/aio/DataDredgingBias name: Data Dredging Bias def: "A use and interpretation bias where testing many hypotheses in a dataset may yield apparent statistical significance even when results are nonsignificant." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Data Dredging" EXACT [] is_a: https://w3id.org/aio/UseAndInterpretationBias ! Use And Interpretation Bias [Term] id: https://w3id.org/aio/DataEnhancement name: DataEnhancement def: "Techniques used to improve the quality diversity and volume of data available for training machine learning models such as data augmentation synthesis and enrichment to enhance model robustness and accuracy." [] subset: https://w3id.org/aio/PreprocessingSubset is_a: https://w3id.org/aio/Preprocessing ! Preprocessing [Term] id: https://w3id.org/aio/DataGenerationBias name: Data Generation Bias def: "A selection and sampling bias arising from adding synthetic or redundant data samples to a dataset." [https://en.wikipedia.org/wiki/Selection_bias] comment: Bias from adding synthetic or redundant data samples to a dataset. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/DataImputation name: Data Imputation def: "A machine learning task focused on methods that replace missing data with substituted values." [https://en.wikipedia.org/wiki/Imputation_(statistics)] comment: Methods that replace missing data with substituted values. subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/DataPreparation name: Data Preparation def: "The process of cleaning transforming and organizing raw data into a suitable format for analysis and modeling ensuring the quality and relevance of the data for machine learning tasks." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Data Assembly" EXACT [] synonym: "Data Curation" EXACT [] synonym: "Data Processing" EXACT [] is_a: https://w3id.org/aio/Preprocessing ! Preprocessing [Term] id: https://w3id.org/aio/DatatoTextLLM name: Data-to-Text LLM def: "A LLM that generates natural language descriptions from structured data sources like tables, graphs, and knowledge bases, requiring grounding in meaning representations." [] subset: https://w3id.org/aio/ModelSubset synonym: "Meaning representation" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/DecisionTree name: Decision Tree def: "A machine learning model that uses a tree-like model of decisions and their possible consequences including chance event outcomes resource costs and utilities." [https://en.wikipedia.org/wiki/Decision_tree] comment: A decision support tool that uses a tree-like model of decisions and their possible consequences, including chance event outcomes, resource costs, and utilities. subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/Classification ! Classification [Term] id: https://w3id.org/aio/DecoderLLM name: Decoder LLM def: "A large language model that uses a decoder-only architecture consisting of only a decoder trained to predict the next token in a sequence given the previous tokens." [https://www.practicalai.io/understanding-transformer-model-architectures/#\:~\:text=Encoder] comment: A decoder-only architecture consisting of only a decoder, trained to predict the next token in a sequence given the previous tokens. Unlike the encoder-decoder architecture, it does not have an explicit encoder and encodes information implicitly in the hidden state of the decoder, updated at each step of the generation process. subset: https://w3id.org/aio/ModelSubset is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/DeconvolutionalNetwork name: Deconvolutional Network def: "A deep neural network that uses deconvolution for unsupervised construction of hierarchical image representations." [https://ieeexplore.ieee.org/document/5539957] comment: Layers: Input, Kernel, Convolutional/Pool, Output subset: https://w3id.org/aio/NetworkSubset synonym: "DN" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network relationship: BFO:0000051 https://w3id.org/aio/ConvolutionalLayer ! has part Convolutional Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/KernelLayer ! has part Kernel Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer relationship: BFO:0000051 https://w3id.org/aio/PoolingLayer ! has part Pooling Layer [Term] id: https://w3id.org/aio/DeepActiveLearning name: Deep Active Learning def: "A deep neural network that combines deep learning and active learning to maximize model performance while annotating the fewest samples possible." [https://arxiv.org/pdf/2009.00236.pdf] subset: https://w3id.org/aio/NetworkSubset synonym: "DeepAL" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/DeepBeliefNetwork name: Deep Belief Network def: "An unsupervised pretrained network composed of multiple layers of latent variables that learns to probabilistically reconstruct inputs and perform classification." [https://en.wikipedia.org/wiki/Deep_belief_network] comment: Layers: Backfed Input, Probabilistic Hidden, Hidden, Matched Output-Input subset: https://w3id.org/aio/NetworkSubset synonym: "DBN" EXACT [] is_a: https://w3id.org/aio/UnsupervisedPretrainedNetwork ! Unsupervised Pretrained Network relationship: BFO:0000051 https://w3id.org/aio/BackfedInputLayer ! has part Backfed Input Layer relationship: BFO:0000051 https://w3id.org/aio/MatchedInputOutputLayer ! has part Matched Input-Output Layer relationship: BFO:0000051 https://w3id.org/aio/ProbabilisticHiddenLayer ! has part Probabilistic Hidden Layer [Term] id: https://w3id.org/aio/DeepConvolutionalInverseGraphicsNetwork name: Deep Convolutional Inverse Graphics Network def: "An autoencoder network that learns interpretable disentangled image representations through convolution and de-convolution layers trained with the stochastic gradient variational Bayes algorithm." [] comment: Layers: Input, Kernel, Convolutional/Pool, Probabilistic Hidden, Convolutional/Pool, Kernel, Output subset: https://w3id.org/aio/NetworkSubset synonym: "DCIGN" EXACT [] is_a: https://w3id.org/aio/AutoEncoderNetwork ! Auto Encoder Network relationship: BFO:0000051 https://w3id.org/aio/ConvolutionalLayer ! has part Convolutional Layer relationship: BFO:0000051 https://w3id.org/aio/KernelLayer ! has part Kernel Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer relationship: BFO:0000051 https://w3id.org/aio/PoolingLayer ! has part Pooling Layer relationship: BFO:0000051 https://w3id.org/aio/ProbabilisticHiddenLayer ! has part Probabilistic Hidden Layer [Term] id: https://w3id.org/aio/DeepConvolutionalNetwork name: Deep Convolutional Network def: "A deep neural network specialized for analyzing visual imagery using shared-weight architecture and translation-equivariant feature maps." [https://en.wikipedia.org/wiki/Convolutional_neural_network] comment: Layers: Input, Kernel, Convolutional/Pool, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "CNN" EXACT [] synonym: "ConvNet" EXACT [] synonym: "Convolutional Neural Network" EXACT [] synonym: "DCN" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network relationship: BFO:0000051 https://w3id.org/aio/ConvolutionalLayer ! has part Convolutional Layer relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/KernelLayer ! has part Kernel Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer relationship: BFO:0000051 https://w3id.org/aio/PoolingLayer ! has part Pooling Layer [Term] id: https://w3id.org/aio/DeepFeedForwardNetwork name: Deep Feed-Forward Network def: "A deep neural network that processes information in one direction—from input nodes through hidden nodes to output nodes—without cycles or loops." [https://en.wikipedia.org/wiki/Feedforward_neural_network] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "DFF" EXACT [] synonym: "MLP" EXACT [] synonym: "Multilayer Perceptoron" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/DeepNeuralNetwork name: Deep Neural Network def: "An artificial neural network characterized by multiple hidden layers between the input and output layers." [] comment: A deep neural network (DNN) is a type of artificial neural network (ANN) characterized by multiple hidden layers between the input and output layers. Each layer consists of interconnected neurons that process and transmit information. DNNs can model complex patterns and representations in data through their hierarchical structure, where each layer extracts increasingly abstract features from the input. DNNs are widely used in various applications, including image and speech recognition, natural language processing, and more, due to their ability to learn and generalize from large amounts of data. subset: https://w3id.org/aio/NetworkSubset synonym: "DNN" EXACT [] is_a: https://w3id.org/aio/ArtificialNeuralNetwork ! Artificial Neural Network [Term] id: https://w3id.org/aio/DeepTransferLearning name: Deep Transfer Learning def: "A deep neural network that relaxes the hypothesis that training data must be independent and identically distributed with test data to address insufficient training data." [https://arxiv.org/abs/1808.01974] subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/DenoisingAutoEncoder name: Denoising Auto Encoder def: "An autoencoder network trained to reconstruct the original undistorted input from a partially corrupted input." [https://doi.org/10.1145/1390156.1390294] comment: Layers: Noisy Input, Hidden, Matched Output-Input subset: https://w3id.org/aio/NetworkSubset synonym: "DAE" EXACT [] synonym: "Denoising Autoencoder" EXACT [] is_a: https://w3id.org/aio/AutoEncoderNetwork ! Auto Encoder Network relationship: BFO:0000051 https://w3id.org/aio/NoisyInputLayer ! has part Noisy Input Layer [Term] id: https://w3id.org/aio/DenseFeaturesLayer name: DenseFeatures Layer def: "A layer that produces a dense tensor based on given feature columns." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/DenseFeatures] comment: A layer that produces a dense Tensor based on given feature_columns. Generally a single example in training data is described with FeatureColumns. At the first layer of the model, this column oriented data should be converted to a single Tensor. This layer can be called multiple times with different features. This is the V2 version of this layer that uses name_scopes to create variables instead of variable_scopes. But this approach currently lacks support for partitioned variables. In that case, use the V1 version instead. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/DenseLayer name: Dense Layer def: "A layer that is a regular densely-connected neural network layer." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense] comment: Just your regular densely-connected NN layer. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/DeploymentBias name: Deployment Bias def: "A bias arising when systems are used as decision aids for humans since the human intermediary may act on predictions in ways that are typically not modeled in the system." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/GroupBias ! Group Bias [Term] id: https://w3id.org/aio/DepthwiseConv1DLayer name: DepthwiseConv1D Layer def: "A layer that performs depthwise 1D convolution" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/DepthwiseConv1D] comment: Depthwise 1D convolution. Depthwise convolution is a type of convolution in which each input channel is convolved with a different kernel (called a depthwise kernel). You can understand depthwise convolution as the first step in a depthwise separable convolution. It is implemented via the following steps: Split the input into individual channels. Convolve each channel with an individual depthwise kernel with depth_multiplier output channels. Concatenate the convolved outputs along the channels axis. Unlike a regular 1D convolution, depthwise convolution does not mix information across different input channels. The depth_multiplier argument determines how many filter are applied to one input channel. As such, it controls the amount of output channels that are generated per input channel in the depthwise step. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/DepthwiseConv2DLayer name: DepthwiseConv2D Layer def: "A layer that performs depthwise 2D convolution" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/DepthwiseConv2D] comment: Depthwise 2D convolution. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/DetectionBias name: Detection Bias def: "A selection and sampling bias characterized by systematic differences between groups in how outcomes are determined potentially over- or underestimating effect size." [https://doi.org/10.6028/NIST.SP.1270] comment: Systematic differences between groups in how outcomes are determined, potentially over- or underestimating effect size. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/DialogueLLM name: Dialogue LLM def: "A large language model that is optimized for engaging in multi-turn conversations understanding context and generating relevant coherent responses continuously over many dialogue turns." [] subset: https://w3id.org/aio/ModelSubset synonym: "conversational AI" RELATED [] synonym: "Dialogue Large Language Model" EXACT [] synonym: "multi-turn dialogue" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/DifferentiableLLM name: Differentiable LLM def: "A large language model that has an architecture amenable to full end-to-end training via backpropagation without relying on teacher forcing or unlikelihood training objectives." [] subset: https://w3id.org/aio/ModelSubset synonym: "Differentiable Large Language Model" EXACT [] synonym: "end-to-end training" RELATED [] synonym: "fully backpropagable" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/DimensionalityReduction name: Dimensionality Reduction def: "A machine learning task focused on the process of transforming data from a high-dimensional space into a lower-dimensional space while retaining meaningful properties of the original data." [https://en.wikipedia.org/wiki/Dimensionality_reduction] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Dimension Reduction" EXACT [] is_a: https://w3id.org/aio/UnsupervisedLearning ! Unsupervised Learning [Term] id: https://w3id.org/aio/DiscretizationLayer name: Discretization Layer def: "A preprocessing layer which buckets continuous features by ranges." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Discretization] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/NumericalFeaturesPreprocessingLayer ! Numerical Features Preprocessing Layer [Term] id: https://w3id.org/aio/Distillation name: Distillation def: "The process of training a smaller model to replicate the behavior of a larger model aiming to compress the knowledge into a more compact form without significant loss of performance." [https://doi.org/10.48550/arXiv.2105.13093] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Knowledge compression" RELATED [] synonym: "Purification" EXACT [] synonym: "Refining" EXACT [] synonym: "Teacher-student model" RELATED [] is_a: https://w3id.org/aio/Preprocessing ! Preprocessing [Term] id: https://w3id.org/aio/DomainAdaptedLLM name: Domain-Adapted LLM def: "A LLM which is pre-trained on a broad corpus and then fine-tuned on domain-specific data to specialize its capabilities for particular domains or applications, like scientific literature or code generation." [] subset: https://w3id.org/aio/ModelSubset synonym: "domain robustness" RELATED [] synonym: "Domain-Adapted Large Language Model" EXACT [] synonym: "transfer learning" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/DotLayer name: Dot Layer def: "A layer that computes a dot product between samples in two tensors." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dot] comment: Layer that computes a dot product between samples in two tensors. E.g. if applied to a list of two tensors a and b of shape (batch_size, n), the output will be a tensor of shape (batch_size, 1) where each entry i will be the dot product between a[i] and b[i]. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/DropoutLayer name: Dropout Layer def: "A regularization layer that applies Dropout to the input" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dropout] comment: Applies Dropout to the input. The Dropout layer randomly sets input units to 0 with a frequency of rate at each step during training time, which helps prevent overfitting. Inputs not set to 0 are scaled up by 1/(1 - rate) such that the sum over all inputs is unchanged. Note that the Dropout layer only applies when training is set to True such that no values are dropped during inference. When using model.fit, training will be appropriately set to True automatically, and in other contexts, you can set the kwarg explicitly to True when calling the layer. (This is in contrast to setting trainable=False for a Dropout layer. trainable does not affect the layer's behavior, as Dropout does not have any variables/weights that can be frozen during training.) subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RegularizationLayer ! Regularization Layer [Term] id: https://w3id.org/aio/DunningKrugerEffectBias name: Dunning-Kruger Effect Bias def: "A cognitive bias in which people with low ability in an area overestimate that ability. Often measured by comparing self-assessment with objective performance." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Dunning-Kruger Effect" EXACT [] is_a: https://w3id.org/aio/CognitiveBias ! Cognitive Bias [Term] id: https://w3id.org/aio/DynamicConditionalCorrelation name: Dynamic Conditional Correlation def: "A model that allows for time-varying correlations between different time series, used in financial econometrics to model and forecast covariances." [] subset: https://w3id.org/aio/ModelSubset synonym: "DCC" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/ELUFunction name: ELU Function def: "An activation function that is x if x > 0 and alpha * (exp(x) - 1) if x < 0 where alpha controls the value to which an ELU saturates for negative net inputs." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/elu] comment: The exponential linear unit (ELU) with alpha > 0 is: x if x > 0 and alpha * (exp(x) - 1) if x < 0 The ELU hyperparameter alpha controls the value to which an ELU saturates for negative net inputs. ELUs diminish the vanishing gradient effect. ELUs have negative values which pushes the mean of the activations closer to zero. Mean activations that are closer to zero enable faster Learning as they bring the gradient closer to the natural gradient. ELUs saturate to a negative value when the argument gets smaller. Saturation means a small derivative which decreases the variation and the information that is propagated to the next layer. subset: https://w3id.org/aio/FunctionSubset synonym: "ELU" EXACT [] synonym: "Exponential Linear Unit" EXACT [] is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/ELULayer name: ELU Layer def: "An activation layer that applies the Exponential Linear Unit (ELU) function element-wise." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ELU] comment: Exponential Linear Unit. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ActivationLayer ! Activation Layer [Term] id: https://w3id.org/aio/EchoStateNetwork name: Echo State Network def: "A recurrent neural network with a recurrent hidden layer and sparsely connected hidden neurons that learns output weights to produce temporal patterns." [https://en.wikipedia.org/wiki/Echo_state_network] comment: Layers: Input, Recurrent, Output subset: https://w3id.org/aio/NetworkSubset synonym: "ESN" EXACT [] is_a: https://w3id.org/aio/RecurrentNeuralNetwork ! Recurrent Neural Network relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer relationship: BFO:0000051 https://w3id.org/aio/RecurrentLayer ! has part Recurrent Layer [Term] id: https://w3id.org/aio/EcologicalFallacyBias name: Ecological Fallacy Bias def: "A selection and sampling bias occurring when an inference about an individual is made based on their group membership." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Ecological Fallacy" EXACT [] is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/EmbeddingLayer name: Embedding Layer def: "A layer that turns positive integers (indexes) into dense vectors of fixed size." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Embedding] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/EmbodiedLLM name: Embodied LLM def: "A large language model that integrates language with other modalities like vision audio and robotics to enable grounded language understanding in real-world environments." [] comment: An embodied LLM integrates language with other modalities like vision, audio, and robotics to enable grounded language understanding in real-world environments. subset: https://w3id.org/aio/ModelSubset synonym: "Embodied Large Language Model" EXACT [] synonym: "multimodal grounding" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/EmergentBias name: Emergent Bias def: "A use and interpretation bias resulting from the use and reliance on algorithms across new or unanticipated contexts." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/UseAndInterpretationBias ! Use And Interpretation Bias [Term] id: https://w3id.org/aio/EncoderDecoderLLM name: Encoder-Decoder LLM def: "The LLM introduced in the \"Attention Is All You Need\" paper. The encoder processes the input sequence to generate a hidden representation summarizing the input information, while the decoder uses this hidden representation to generate the desired output sequence." [https://www.practicalai.io/understanding-transformer-model-architectures/#\:~\:text=Encoder] subset: https://w3id.org/aio/ModelSubset is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/EncoderLLM name: Encoder LLM def: "A large language model that uses an encoder-only architecture to encode the input sequence into a fixed-length representation which is then used as input to a classifier or regressor for prediction." [https://www.practicalai.io/understanding-transformer-model-architectures/#\:~\:text=Encoder] comment: An encoder-only architecture that encodes the input sequence into a fixed-length representation, which is then used as input to a classifier or regressor for prediction. The model has a pre-trained general-purpose encoder that requires fine-tuning for specific tasks. subset: https://w3id.org/aio/ModelSubset is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/EnergyBasedLLM name: Energy-Based LLM def: "A LLM which models the explicit probability density over token sequences using an energy function, rather than an autoregressive factorization. This can improve modeling of long-range dependencies and global coherence." [] subset: https://w3id.org/aio/ModelSubset synonym: "energy scoring" RELATED [] synonym: "Energy-Based Large Language Model" EXACT [] synonym: "explicit density modeling" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/EnsembleLearning name: Ensemble Learning def: "A type of machine learning focused on methods that use multiple learning algorithms to achieve better predictive performance than any of the constituent algorithms alone." [https://en.wikipedia.org/wiki/Ensemble_learning] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/ErrorPropagationBias name: Error Propagation Bias def: "A processing bias characterized by the effect of variables' uncertainties (or errors more specifically random errors) on the uncertainty of a function based on them." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Error Propagation" EXACT [] is_a: https://w3id.org/aio/ProcessingBias ! Processing Bias [Term] id: https://w3id.org/aio/EthicalLLM name: Ethical LLM def: "A large language model that is trained to uphold certain ethical principles values or rules in its language generation to increase safety and trustworthiness." [] subset: https://w3id.org/aio/ModelSubset synonym: "constituitional AI" RELATED [] synonym: "Ethical Large Language Model" EXACT [] synonym: "value alignment" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/EvaluationBias name: Evaluation Bias def: "A selection and sampling bias arising when testing populations do not equally represent user populations or when inappropriate performance metrics are used." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/EvolutionaryLLM name: Evolutionary LLM def: "A large language model that applies principles of evolutionary computation to optimize its structure and parameters evolving over time to improve performance." [] subset: https://w3id.org/aio/ModelSubset synonym: "evolutionary algorithms" RELATED [] synonym: "Evolutionary Language Model" EXACT [] synonym: "genetic programming" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ExclusionBias name: Exclusion Bias def: "A selection and sampling bias occurring when specific groups of user populations are excluded from testing and analysis." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/ExplainableLLM name: Explainable LLM def: "A large language model that is designed to provide insights into its decision-making process making it easier for users to understand and trust the model's outputs by incorporating mechanisms for interpreting and explaining its predictions in human-understandable terms." [] subset: https://w3id.org/aio/ModelSubset synonym: "Explainable Language Model" EXACT [] synonym: "interpretability" RELATED [] synonym: "model understanding" RELATED [] synonym: "XAI LLM" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ExponentialFunction name: Exponential Function def: "An activation function that is the mathematical function denoted by f(x)=exp or e^{x}." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/exponential] comment: The exponential function is a mathematical function denoted by f(x)=exp or e^\{x\}. subset: https://w3id.org/aio/FunctionSubset is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/ExponentialSmoothingStateSpaceModel name: Exponential Smoothing State Space Model def: "A model that combines exponential smoothing with state space modeling, allowing for the inclusion of both trend and seasonal components. Used in forecasting." [] subset: https://w3id.org/aio/ModelSubset synonym: "ETS" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/ExtremeLearningMachine name: Extreme Learning Machine def: "A feedback network with randomly assigned hidden nodes that are not updated during training." [https://en.wikipedia.org/wiki/Extreme_Learning_machine] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "ELM" EXACT [] is_a: https://w3id.org/aio/FeedbackNetwork ! Feedback Network [Term] id: https://w3id.org/aio/FactoredLanguageModel name: Factored Language Model def: "A language model that views each word as a vector of multiple factors such as part-of-speech morphology and semantics to improve language modeling." [https://en.wikipedia.org/wiki/Factored_language_model] subset: https://w3id.org/aio/ModelSubset synonym: "Factorized Language Model" EXACT [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/FactorizedLLM name: Factorized LLM def: "A large language model that decomposes the full language modeling task into multiple sub-components or experts that each focus on a subset of the information enabling more efficient scaling." [https://doi.org/10.48550/arXiv.2403.12556] subset: https://w3id.org/aio/ModelSubset synonym: "Conditional masking" RELATED [] synonym: "Factorized Large Language Model" EXACT [] synonym: "Factorized Learning Assisted with Large Language Model" EXACT [] synonym: "Product of experts" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/FeatureExtraction name: Feature Extraction def: "The process of transforming raw data into a set of measurable characteristics that can be used as input for machine learning algorithms enhancing the ability to make accurate predictions." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Attribute Extraction" EXACT [] synonym: "Feature Isolation" EXACT [] synonym: "Semantic embeddings" RELATED [] synonym: "Syntactic information" RELATED [] is_a: https://w3id.org/aio/DataEnhancement ! DataEnhancement [Term] id: https://w3id.org/aio/FederatedLLM name: Federated LLM def: "A large language model that is trained in a decentralized manner across multiple devices or silos without directly sharing private data enabling collaborative training while preserving data privacy and security." [] subset: https://w3id.org/aio/ModelSubset synonym: "decentralized training" RELATED [] synonym: "Federated Large Language Model" EXACT [] synonym: "privacy-preserving" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/FederatedLearning name: Federated Learning def: "A deep neural network trained across decentralized edge devices or servers holding local data samples without exchanging them." [https://en.wikipedia.org/wiki/Federated_learning] comment: Training an algorithm across multiple decentralized edge devices or servers holding local data samples without exchanging them. subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/FeedbackLoopBias name: Feedback Loop Bias def: "A use and interpretation bias occurring when an algorithm learns from user behavior and feeds that behavior back into the model." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/UseAndInterpretationBias ! Use And Interpretation Bias [Term] id: https://w3id.org/aio/FeedbackNetwork name: Feedback Network def: "An artificial neural network that refines its representations iteratively based on feedback from previous outputs." [] comment: Layers: Input, Hidden, Output, Hidden subset: https://w3id.org/aio/NetworkSubset synonym: "FBN" EXACT [] is_a: https://w3id.org/aio/ArtificialNeuralNetwork ! Artificial Neural Network relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/FixedEffectsModel name: Fixed Effects Model def: "A regression analysis model in which the model parameters are fixed or non-random quantities." [https://en.wikipedia.org/wiki/Fixed_effects_model] subset: https://w3id.org/aio/MachineLearningSubset synonym: "FEM" EXACT [] is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/FlattenLayer name: Flatten Layer def: "A layer that flattens the input" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Flatten] comment: Flattens the input. Does not affect the batch size. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/FractionalMaxPool2DLayer name: FractionalMaxPool2D Layer def: "A pooling layer that applies a 2D fractional max pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "FractionalMaxPool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/FractionalMaxPool3DLayer name: FractionalMaxPool3D Layer def: "A pooling layer that applies a 3D fractional max pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "FractionalMaxPool3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/Function name: Function def: "A mathematical rule that gives the value of a dependent variable corresponding to specified values of independent variables." [https://www.sciencedirect.com/topics/mathematics/mathematical-function] subset: https://w3id.org/aio/ClassSubset [Term] id: https://w3id.org/aio/FundingBias name: Funding Bias def: "A bias arising when biased results are reported to support or satisfy the funding agency or financial supporter of a research study." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/GroupBias ! Group Bias [Term] id: https://w3id.org/aio/GELUFunction name: GELU Function def: "An activation function that computes x * P(X <= x) where P(X) ~ N(0 1) weighting inputs by their value rather than gating inputs by their sign as in ReLU." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/gelu] comment: Gaussian error linear unit (GELU) computes x * P(X <= x), where P(X) ~ N(0, 1). The (GELU) nonlinearity weights inputs by their value, rather than gates inputs by their sign as in ReLU. subset: https://w3id.org/aio/FunctionSubset synonym: "Gaussian Error Linear Unit" EXACT [] synonym: "GELU" EXACT [] is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/GRUCellLayer name: GRUCell Layer def: "A layer that processes one step within the whole time sequence input for a GRU layer." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GRUCell] comment: Cell class for the GRU layer. This class processes one step within the whole time sequence input, whereas tf.keras.layer.GRU processes the whole sequence. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/GRULayer name: GRU Layer def: "A recurrent layer that implements the Gated Recurrent Unit architecture." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GRU] comment: Gated Recurrent Unit - Cho et al. 2014. Based on available runtime hardware and constraints, this layer will choose different implementations (cuDNN-based or pure-TensorFlow) to maximize the performance. If a GPU is available and all the arguments to the layer meet the requirement of the cuDNN kernel (see below for details), the layer will use a fast cuDNN implementation. The requirements to use the cuDNN implementation are: activation == tanh, recurrent_activation == sigmoid, recurrent_dropout == 0, unroll is False, use_bias is True, reset_after is True. Inputs, if use masking, are strictly right-padded. Eager execution is enabled in the outermost context. There are two variants of the GRU implementation. The default one is based on v3 and has reset gate applied to hidden state before matrix multiplication. The other one is based on original and has the order reversed. The second variant is compatible with CuDNNGRU (GPU-only) and allows inference on CPU. Thus it has separate biases for kernel and recurrent_kernel. To use this variant, set reset_after=True and recurrent_activation='sigmoid'. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RecurrentLayer ! Recurrent Layer [Term] id: https://w3id.org/aio/GatedRecurrentUnit name: Gated Recurrent Unit def: "A long short-term memory network that is a gating mechanism in recurrent neural networks similar to LSTMs but with fewer parameters and no output gate." [https://en.wikipedia.org/wiki/Gated_recurrent_unit] comment: Layers: Input, Memory Cell, Output subset: https://w3id.org/aio/NetworkSubset synonym: "GRU" EXACT [] is_a: https://w3id.org/aio/LongShortTermMemory ! Long Short Term Memory [Term] id: https://w3id.org/aio/GaussianDropoutLayer name: GaussianDropout Layer def: "A regularization layer that applies multiplicative 1-centered Gaussian noise." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GaussianDropout] comment: Apply multiplicative 1-centered Gaussian noise. As it is a regularization layer, it is only active at training time. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RegularizationLayer ! Regularization Layer [Term] id: https://w3id.org/aio/GaussianNoiseLayer name: GaussianNoise Layer def: "A regularization layer that applies additive zero-centered Gaussian noise." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GaussianNoise] comment: Apply additive zero-centered Gaussian noise. This is useful to mitigate overfitting (you could see it as a form of random data augmentation). Gaussian Noise (GS) is a natural choice as corruption process for real valued inputs. As it is a regularization layer, it is only active at training time. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RegularizationLayer ! Regularization Layer [Term] id: https://w3id.org/aio/GeneralizedAutoregressiveConditionalHeteroskedasticity name: Generalized Autoregressive Conditional Heteroskedasticity def: "A model that incorporates lagged conditional variances, allowing for more flexibility in modeling time-varying volatility." [] subset: https://w3id.org/aio/ModelSubset synonym: "GARCH" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/GeneralizedFewshotLearning name: Generalized Few-shot Learning def: "A deep neural network that learns novel classes from few samples per class, preventing catastrophic forgetting of base classes and ensuring classifier calibration." [https://paperswithcode.com/paper/generalized-and-incremental-few-shot-learning/review/] subset: https://w3id.org/aio/NetworkSubset synonym: "GFSL" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/GeneralizedLinearModel name: Generalized Linear Model def: "A machine learning model that generalizes linear regression by relating the linear model to the response variable via a link function and allowing the variance of each measurement to be a function of its predicted value." [https://en.wikipedia.org/wiki/Generalized_linear_model] subset: https://w3id.org/aio/MachineLearningSubset synonym: "GLM" EXACT [] is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/GenerativeAdversarialNetwork name: Generative Adversarial Network def: "An unsupervised pretrained network framework where two neural networks contest in a game to generate new data with the same statistics as the training set." [https://en.wikipedia.org/wiki/Generative_adversarial_network] comment: Layers: Backfed Input, Hidden, Matched Output-Input, Hidden, Matched Output-Input subset: https://w3id.org/aio/NetworkSubset synonym: "GAN" EXACT [] is_a: https://w3id.org/aio/UnsupervisedPretrainedNetwork ! Unsupervised Pretrained Network relationship: BFO:0000051 https://w3id.org/aio/BackfedInputLayer ! has part Backfed Input Layer relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/MatchedInputOutputLayer ! has part Matched Input-Output Layer [Term] id: https://w3id.org/aio/GenerativeAdversarialNetworkAugmentedLLM name: Generative Adversarial Network-Augmented LLM def: "A LLM which incorporates a generative adversarial network (GAN) into its training process, using a discriminator network to provide a signal for generating more realistic and coherent text. This adversarial training can improve the quality and diversity of generated text." [] subset: https://w3id.org/aio/ModelSubset synonym: "adversarial training" RELATED [] synonym: "GAN-Large Language Model" EXACT [] synonym: "Generative Adversarial Network-Augmented Large Language Model" EXACT [] synonym: "text generation" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/GenerativeCommonsenseLLM name: Generative Commonsense LLM def: "A large language model that is trained to understand and model basic physics causality and common sense about how the real world works." [https://arxiv.org/abs/2306.12672] subset: https://w3id.org/aio/ModelSubset synonym: "causal modeling" RELATED [] synonym: "Generative Commonsense Large Language Model" EXACT [] synonym: "physical reasoning" RELATED [] synonym: "World Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/GenerativeLanguageInterface name: Generative Language Interface def: "A language model that enables users to engage in an interactive dialogue with an LLM providing feedback to guide and refine the generated outputs iteratively." [] subset: https://w3id.org/aio/ModelSubset synonym: "Interactive generation" RELATED [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/GlobalAveragePooling1DLayer name: GlobalAveragePooling1D Layer def: "A pooling layer that performs global average pooling operation for temporal data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling1D] comment: Global average pooling operation for temporal data. subset: https://w3id.org/aio/LayerSubset synonym: "GlobalAvgPool1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/GlobalAveragePooling2DLayer name: GlobalAveragePooling2D Layer def: "A pooling layer that performs global average pooling operation for spatial data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling2D] comment: Global average pooling operation for spatial data. subset: https://w3id.org/aio/LayerSubset synonym: "GlobalAvgPool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/GlobalAveragePooling3DLayer name: GlobalAveragePooling3D Layer def: "A pooling layer that performs global average pooling operation for 3D data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling3D] comment: Global Average pooling operation for 3D data. subset: https://w3id.org/aio/LayerSubset synonym: "GlobalAvgPool3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/GlobalMaxPooling1DLayer name: GlobalMaxPooling1D Layer def: "A pooling layer that performs global max pooling operation for temporal data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool1D] comment: Global max pooling operation for 1D temporal data. subset: https://w3id.org/aio/LayerSubset synonym: "GlobalMaxPool1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/GlobalMaxPooling2DLayer name: GlobalMaxPooling2D Layer def: "A pooling layer that performs global max pooling operation for spatial data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool2D] comment: Global max pooling operation for spatial data. subset: https://w3id.org/aio/LayerSubset synonym: "GlobalMaxPool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/GlobalMaxPooling3DLayer name: GlobalMaxPooling3D Layer def: "A pooling layer that performs global max pooling operation for 3D data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool3D] comment: Global Max pooling operation for 3D data. subset: https://w3id.org/aio/LayerSubset synonym: "GlobalMaxPool3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/GraphConvolutionalNetwork name: Graph Convolutional Network def: "A deep neural network that operates directly on graph structures utilizing structural information." [https://arxiv.org/abs/1609.02907] comment: Layers: Input, Hidden, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "GCN" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/GraphConvolutionalPolicyNetwork name: Graph Convolutional Policy Network def: "A graph convolutional network that generates goal-directed graphs using reinforcement learning and optimizing for rewards and adversarial loss." [https://arxiv.org/abs/1806.02473] comment: Layers: Input, Hidden, Hidden, Policy, Output subset: https://w3id.org/aio/NetworkSubset synonym: "GPCN" EXACT [] is_a: https://w3id.org/aio/GraphConvolutionalNetwork ! Graph Convolutional Network relationship: BFO:0000051 https://w3id.org/aio/PolicyLayer ! has part Policy Layer [Term] id: https://w3id.org/aio/GraphLanguageModel name: Graph Language Model def: "A language model that operates over structured inputs or outputs represented as graphs enabling reasoning over explicit relational knowledge representations during language tasks." [https://arxiv.org/abs/2401.07105] subset: https://w3id.org/aio/ModelSubset synonym: "Graph LM" EXACT [] synonym: "Structured representations" RELATED [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/GroupBias name: Group Bias def: "A bias characterized by favoring members of one's in-group over out-group members expressed in evaluation resource allocation and other ways." [https://en.wikipedia.org/wiki/In-group_favoritism] comment: Favoring members of one's in-group over out-group members, expressed in evaluation, resource allocation, and other ways. subset: https://w3id.org/aio/BiasSubset synonym: "In-group bias" EXACT [] synonym: "In-group Favoritism" EXACT [] synonym: "In-group preference" EXACT [] synonym: "In-group–out-group Bias" EXACT [] synonym: "Intergroup bias" EXACT [] is_a: https://w3id.org/aio/HumanBias ! Human Bias [Term] id: https://w3id.org/aio/GroupNormLayer name: GroupNorm Layer def: "A normalization layer that applies Group Normalization over a mini-batch of inputs." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Group Normalization over a mini-batch of inputs as described in the paper Group Normalization subset: https://w3id.org/aio/LayerSubset synonym: "GroupNorm" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/GroupthinkBias name: Groupthink Bias def: "A psychological phenomenon where people in a group make non-optimal decisions due to a desire to conform or fear of dissent." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Groupthink" EXACT [] is_a: https://w3id.org/aio/GroupBias ! Group Bias [Term] id: https://w3id.org/aio/HardSigmoidFunction name: Hard Sigmoid Function def: "An activation function that is a faster approximation of the sigmoid activation using a piecewise linear approximation." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/hard_sigmoid] comment: A faster approximation of the sigmoid activation. Piecewise linear approximation of the sigmoid function. Ref: 'https://en.wikipedia.org/wiki/Hard_sigmoid' subset: https://w3id.org/aio/FunctionSubset is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/HashingLayer name: Hashing Layer def: "A categorical features preprocessing layer which hashes and bins categorical features." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Hashing] comment: A preprocessing layer which hashes and bins categorical features. This layer transforms categorical inputs to hashed output. It element-wise converts a ints or strings to ints in a fixed range. The stable hash function uses tensorflow::ops::Fingerprint to produce the same output consistently across all platforms. This layer uses FarmHash64 by default, which provides a consistent hashed output across different platforms and is stable across invocations, regardless of device and context, by mixing the input bits thoroughly. If you want to obfuscate the hashed output, you can also pass a random salt argument in the constructor. In that case, the layer will use the SipHash64 hash function, with the salt value serving as additional input to the hash function. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/CategoricalFeaturesPreprocessingLayer ! Categorical Features Preprocessing Layer [Term] id: https://w3id.org/aio/HiddenLayer name: Hidden Layer def: "A layer located between the input and output that performs nonlinear transformations of the inputs entered into the network." [https://deepai.org/machine-Learning-glossary-and-terms/hidden-layer-machine-Learning] comment: A hidden layer is located between the input and output of the algorithm, in which the function applies weights to the inputs and directs them through an activation function as the output. In short, the hidden layers perform nonlinear transformations of the inputs entered into the network. Hidden layers vary depending on the function of the neural network, and similarly, the layers may vary depending on their associated weights. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/HierarchicalClassification name: Hierarchical Classification def: "A classification task focused on methods that group things according to a hierarchy." [https://en.wikipedia.org/wiki/Hierarchical_classification] comment: Methods that group things according to a hierarchy. subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/Classification ! Classification [Term] id: https://w3id.org/aio/HierarchicalClustering name: Hierarchical Clustering def: "A clustering method that builds a hierarchy of clusters." [https://en.wikipedia.org/wiki/Hierarchical_clustering] comment: Methods that build a hierarchy of clusters. subset: https://w3id.org/aio/MachineLearningSubset synonym: "HCL" EXACT [] is_a: https://w3id.org/aio/Clustering ! Clustering [Term] id: https://w3id.org/aio/HierarchicalLanguageModel name: Hierarchical Language Model def: "A language model that represents language at multiple levels of granularity learning hierarchical representations that capture both low-level patterns and high-level abstractions." [https://doi.org/10.1016/j.ipm.2024.103698] subset: https://w3id.org/aio/ModelSubset synonym: "Hierarchical LM" EXACT [] synonym: "multi-scale representations" RELATED [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/HistoricalBias name: Historical Bias def: "A bias characterized by long-standing biases encoded in society over time distinct from biases in historical description or interpretation." [https://doi.org/10.6028/NIST.SP.1270] comment: Long-standing biases encoded in society over time, distinct from biases in historical description or the interpretation of history, such as viewing the larger world from a Western or European perspective. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/Bias ! Bias [Term] id: https://w3id.org/aio/HopfieldNetwork name: Hopfield Network def: "A symmetrically connected network that is a type of recurrent artificial neural network serving as a content-addressable memory system." [https://en.wikipedia.org/wiki/Hopfield_network] comment: Layers: Backfed input subset: https://w3id.org/aio/NetworkSubset synonym: "HN" EXACT [] synonym: "Ising model of a neural network" EXACT [] synonym: "Ising–Lenz–Little model" EXACT [] is_a: https://w3id.org/aio/SymmetricallyConnectedNetwork ! Symmetrically Connected Network relationship: BFO:0000051 https://w3id.org/aio/BackfedInputLayer ! has part Backfed Input Layer [Term] id: https://w3id.org/aio/HostileAttributionBias name: Hostile Attribution Bias def: "A use and interpretation bias where individuals perceive benign or ambiguous behaviors as hostile." [https://en.wikipedia.org/wiki/Interpretive_bias] comment: Bias where individuals perceive benign or ambiguous behaviors as hostile. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/UseAndInterpretationBias ! Use And Interpretation Bias [Term] id: https://w3id.org/aio/HumanBias name: Human Bias def: "A systematic error in human thought based on heuristic principles leading to simplified judgmental operations." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/Bias ! Bias [Term] id: https://w3id.org/aio/HumanReportingBias name: Human Reporting Bias def: "An individual bias that arises when users depend on automated systems as heuristic substitutes for their own information-seeking and processing efforts." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/ImageAugmentationLayer name: Image Augmentation Layer def: "A layer that performs image data preprocessing augmentations." [https://keras.io/guides/preprocessing_layers/] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/ImagePreprocessingLayer name: Image Preprocessing Layer def: "A layer that performs image data preprocessing operations." [https://keras.io/guides/preprocessing_layers/] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/ImplicitBias name: Implicit Bias def: "An individual bias characterized by unconscious beliefs attitudes feelings associations or stereotypes that affect information processing decision-making and actions." [https://doi.org/10.6028/NIST.SP.1270] comment: Unconscious beliefs, attitudes, feelings, associations, or stereotypes that affect information processing, decision-making, and actions. subset: https://w3id.org/aio/BiasSubset synonym: "Confirmatory Bias" EXACT [] is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/ImplicitLanguageModel name: Implicit Language Model def: "A language model that uses an energy function to score entire sequences instead of factorizing probabilities autoregressively better capturing global properties and long-range dependencies." [https://arxiv.org/pdf/2303.16189] subset: https://w3id.org/aio/ModelSubset synonym: "Energy-based models" RELATED [] synonym: "Implicit LM" EXACT [] synonym: "Token-level scoring" RELATED [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/IncremenetalFewshotLearning name: Incremenetal Few-shot Learning def: "A deep neural network trained on a base set of classes and then presented with novel classes, each with few labeled examples." [https://arxiv.org/abs/1810.07218] subset: https://w3id.org/aio/NetworkSubset synonym: "IFSL" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/IndividualBias name: Individual Bias def: "A persistent point of view or limited list of such points of view applied by an individual." [https://develop.consumerium.org/wiki/Individual_bias] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/Bias ! Bias [Term] id: https://w3id.org/aio/InheritedBias name: Inherited Bias def: "A processing bias arising when machine learning applications generate inputs for other machine learning algorithms passing on any existing bias." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/ProcessingBias ! Processing Bias [Term] id: https://w3id.org/aio/InputLayer name: Input Layer def: "A layer composed of artificial input neurons that brings the initial data into the system for further processing by subsequent layers." [https://www.techopedia.com/definition/33262/input-layer-neural-networks] comment: The input layer of a neural network is composed of artificial input neurons, and brings the initial data into the system for further processing by subsequent layers of artificial neurons. The input layer is the very beginning of the workflow for the artificial neural network. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/InputLayerLayer name: InputLayer Layer def: "A layer to be used as an entry point into a Network (a graph of layers)." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/InputLayer] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/InputSpecLayer name: InputSpec Layer def: "A layer that specifies the rank" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/InputSpec] comment: Specifies the rank, dtype and shape of every input to a layer. Layers can expose (if appropriate) an input_spec attribute: an instance of InputSpec, or a nested structure of InputSpec instances (one per input tensor). These objects enable the layer to run input compatibility checks for input structure, input rank, input shape, and input dtype. A None entry in a shape is compatible with any dimension, a None shape is compatible with any shape. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/InstanceNorm1DLayer name: InstanceNorm1D Layer def: "A normalization layer that applies Instance Normalization over a 2D (unbatched) or 3D (batched) input." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Instance Normalization over a 2D (unbatched) or 3D (batched) input as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization. subset: https://w3id.org/aio/LayerSubset synonym: "InstanceNorm1D" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/InstanceNorm2D name: InstanceNorm2D def: "A normalization layer that applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension)." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension) as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/InstanceNorm3DLayer name: InstanceNorm3D Layer def: "A normalization layer that applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension)." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization. subset: https://w3id.org/aio/LayerSubset synonym: "InstanceNorm3D" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/InstitutionalBias name: Institutional Bias def: "A bias exhibited at the level of entire institutions where practices or norms result in the favoring or disadvantaging of certain social groups." [https://doi.org/10.6028/NIST.SP.1270] comment: Bias exhibited at the level of entire institutions, where practices or norms result in the favoring or disadvantaging of certain social groups, such as institutional racism or sexism. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/Bias ! Bias [Term] id: https://w3id.org/aio/InstructionTunedLLM name: Instruction-Tuned LLM def: "A LLM which is fine-tuned to follow natural language instructions accurately and safely, learning to map from instructions to desired model behavior in a more controlled and principled way." [] subset: https://w3id.org/aio/ModelSubset synonym: "constitutional AI" RELATED [] synonym: "Instruction-Tuned Large Language Model" EXACT [] synonym: "natural language instructions" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/IntegerLookupLayer name: IntegerLookup Layer def: "A categorical features preprocessing layer that maps integer features to contiguous ranges." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/IntegerLookup] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/CategoricalFeaturesPreprocessingLayer ! Categorical Features Preprocessing Layer [Term] id: https://w3id.org/aio/InterpretationBias name: Interpretation Bias def: "An individual bias where users interpret algorithmic outputs according to their internalized biases and views." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/KernelLayer name: Kernel Layer def: "A layer that obtains the dot product of input values or subsets of input values." [] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/KnearestNeighborAlgorithm name: K-nearest Neighbor Algorithm def: "A machine learning that groups objects by a plurality vote of its neighbors, assigning each object to the class most common among its k nearest neighbors." [https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm] subset: https://w3id.org/aio/MachineLearningSubset synonym: "K-NN" EXACT [] synonym: "KNN" EXACT [] is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/KnearestNeighborClassificationAlgorithm name: K-nearest Neighbor Classification Algorithm def: "A classification and clustering that classifies objects by a plurality vote of its neighbors, assigning each object to the class most common among its k nearest neighbors." [https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm] subset: https://w3id.org/aio/MachineLearningSubset synonym: "K-NN" EXACT [] synonym: "KNN" EXACT [] is_a: https://w3id.org/aio/Classification ! Classification is_a: https://w3id.org/aio/Clustering ! Clustering [Term] id: https://w3id.org/aio/KnearestNeighborRegressionAlgorithm name: K-nearest Neighbor Regression Algorithm def: "An regression analysis that assigns the average of the values of k nearest neighbors to objects." [https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm] subset: https://w3id.org/aio/MachineLearningSubset synonym: "K-NN" EXACT [] synonym: "KNN" EXACT [] is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/KnowledgeGroundedLLM name: Knowledge-Grounded LLM def: "A LLM which incorporates external knowledge sources or knowledge bases into the model architecture, enabling it to generate more factually accurate and knowledge-aware text." [] subset: https://w3id.org/aio/ModelSubset synonym: "factual grounding" RELATED [] synonym: "knowledge integration" RELATED [] synonym: "Knowledge-Grounded Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/KnowledgeTransfer name: Knowledge Transfer def: "The process by which knowledge is passed from one entity such as a person organization or system to another facilitating learning and adaptation in the receiving entity through various methods such as teaching training or data exchange." [https://doi.org/10.1016/j.knosys.2015.01.010] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Adaptation" RELATED [] synonym: "Inductive Transfer" EXACT [] synonym: "Pretrained models" RELATED [] synonym: "Skill Acquisition" EXACT [] is_a: https://w3id.org/aio/TrainingStrategies ! Training Strategies [Term] id: https://w3id.org/aio/KohonenNetwork name: Kohonen Network def: "A network that is an unsupervised technique producing a low-dimensional representation of high-dimensional data preserving topological structure." [https://en.wikipedia.org/wiki/Self-organizing_map] comment: Layers: Input, Hidden subset: https://w3id.org/aio/NetworkSubset synonym: "KN" EXACT [] synonym: "Self-Organizing Feature Map" EXACT [] synonym: "Self-Organizing Map" EXACT [] synonym: "SOFM" EXACT [] synonym: "SOM" EXACT [] is_a: https://w3id.org/aio/Network ! Network relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer [Term] id: https://w3id.org/aio/LPPool1DLayer name: LPPool1D Layer def: "A pooling layer that applies 1D power-average pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "LPPool1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/LPPool2DLayer name: LPPool2D Layer def: "A pooling layer that applies 2D power-average pooling over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#pooling-layers] subset: https://w3id.org/aio/LayerSubset synonym: "LPPool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/LSTMCellLayer name: LSTMCell Layer def: "A layer that processes one step within the whole time sequence input for an LSTM layer." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTMCell] comment: Cell class for the LSTM layer. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/LSTMLayer name: LSTM Layer def: "A recurrent layer that implements the Long Short-Term Memory architecture." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTM] comment: Long Short-Term Memory layer - Hochreiter 1997. Based on available runtime hardware and constraints, this layer will choose different implementations (cuDNN-based or pure-TensorFlow) to maximize the performance. If a GPU is available and all the arguments to the layer meet the requirement of the cuDNN kernel (see below for details), the layer will use a fast cuDNN implementation. The requirements to use the cuDNN implementation are: 1. activation == tanh, 2. recurrent_activation == sigmoid, 3. recurrent_dropout == 0, 4. unroll is False, 5. use_bias is True, 6. Inputs, if use masking, are strictly right-padded, 7. Eager execution is enabled in the outermost context. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RecurrentLayer ! Recurrent Layer [Term] id: https://w3id.org/aio/LambdaLayer name: Lambda Layer def: "A layer that wraps arbitrary expressions as a Layer object." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Lambda] comment: Wraps arbitrary expressions as a Layer object. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/LanguageInterfaceLLM name: Language Interface LLM def: "A large language model that supports interactive semantic parsing enabling users to provide feedback and corrections to dynamically refine and update the language model." [] subset: https://w3id.org/aio/ModelSubset synonym: "Interactive learning" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/LanguageModel name: Language Model def: "A model designed to predict the next word in a sequence or assign probabilities to sequences of words in natural language." [https://en.wikipedia.org/wiki/Language_model] subset: https://w3id.org/aio/ModelSubset is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/LargeLanguageModel name: Large Language Model def: "A language model consisting of a neural network with many parameters (typically billions of weights or more) trained on large quantities of unlabeled text using self-supervised learning or semi-supervised learning." [https://en.wikipedia.org/wiki/Large_language_model] subset: https://w3id.org/aio/ModelSubset synonym: "LLM" EXACT [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/LassoRegression name: Lasso Regression def: "A regression analysis method that performs both variable selection and regularization to enhance prediction accuracy and interpretability." [https://en.wikipedia.org/wiki/Lasso_(statistics)] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/Layer name: Layer def: "A structure or network topology in a deep learning model that takes information from previous layers and passes it to the next layer." [https://en.wikipedia.org/wiki/Layer_(deep_learning)] subset: https://w3id.org/aio/ClassSubset [Term] id: https://w3id.org/aio/LayerLayer name: Layer Layer def: "The base class from which all layers inherit." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Layer] comment: This is the class from which all layers inherit. A layer is a callable object that takes as input one or more tensors and that outputs one or more tensors. It involves computation, defined in the call() method, and a state (weight variables). State can be created in various places, at the convenience of the subclass implementer: in __init__(); in the optional build() method, which is invoked by the first __call__() to the layer, and supplies the shape(s) of the input(s), which may not have been known at initialization time; in the first invocation of call(), with some caveats discussed below. Users will just instantiate a layer and then treat it as a callable. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/LayerNormLayer name: LayerNorm Layer def: "A normalization layer that applies Layer Normalization over a mini-batch of inputs." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Layer Normalization over a mini-batch of inputs as described in the paper Layer Normalization subset: https://w3id.org/aio/LayerSubset synonym: "LayerNorm" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/LayerNormalizationLayer name: LayerNormalization Layer def: "A normalization layer that applies Layer Normalization over the inputs." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/LayerNormalization] comment: Layer normalization layer (Ba et al., 2016). Normalize the activations of the previous layer for each given example in a batch independently, rather than across a batch like Batch Normalization. i.e. applies a transformation that maintains the mean activation within each example close to 0 and the activation standard deviation close to 1. Given a tensor inputs, moments are calculated and normalization is performed across the axes specified in axis. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/LazyBatchNorm1DLayer name: LazyBatchNorm1D Layer def: "A batch normalization layer that lazily initializes the num_features argument from the input size for 1D data." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: A torch.nn.BatchNorm1D module with lazy initialization of the num_features argument of the BatchNorm1D that is inferred from the input.size(1). subset: https://w3id.org/aio/LayerSubset synonym: "LazyBatchNorm1D" EXACT [] is_a: https://w3id.org/aio/BatchNormalizationLayer ! BatchNormalization Layer [Term] id: https://w3id.org/aio/LazyBatchNorm2DLayer name: LazyBatchNorm2D Layer def: "A batch normalization layer that lazily initializes the num_features argument from the input size for 2D data." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: A torch.nn.BatchNorm2D module with lazy initialization of the num_features argument of the BatchNorm2D that is inferred from the input.size(1). subset: https://w3id.org/aio/LayerSubset synonym: "LazyBatchNorm2D" EXACT [] is_a: https://w3id.org/aio/BatchNormalizationLayer ! BatchNormalization Layer [Term] id: https://w3id.org/aio/LazyBatchNorm3DLayer name: LazyBatchNorm3D Layer def: "A batch normalization layer that lazily initializes the num_features argument from the input size for 3D data." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: A torch.nn.BatchNorm3D module with lazy initialization of the num_features argument of the BatchNorm3D that is inferred from the input.size(1). subset: https://w3id.org/aio/LayerSubset synonym: "LazyBatchNorm3D" EXACT [] is_a: https://w3id.org/aio/BatchNormalizationLayer ! BatchNormalization Layer [Term] id: https://w3id.org/aio/LazyInstanceNorm1DLayer name: LazyInstanceNorm1D Layer def: "An instance normalization layer that lazily initializes the num_features argument from the input size for 1D data." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: A torch.nn.InstanceNorm1D module with lazy initialization of the num_features argument of the InstanceNorm1D that is inferred from the input.size(1). subset: https://w3id.org/aio/LayerSubset synonym: "LazyInstanceNorm1D" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/LazyInstanceNorm2DLayer name: LazyInstanceNorm2D Layer def: "An instance normalization layer that lazily initializes the num_features argument from the input size for 2D data." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: A torch.nn.InstanceNorm2D module with lazy initialization of the num_features argument of the InstanceNorm2D that is inferred from the input.size(1). subset: https://w3id.org/aio/LayerSubset synonym: "LazyInstanceNorm2D" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/LazyInstanceNorm3DLayer name: LazyInstanceNorm3D Layer def: "An instance normalization layer that lazily initializes the num_features argument from the input size for 3D data." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: A torch.nn.InstanceNorm3D module with lazy initialization of the num_features argument of the InstanceNorm3D that is inferred from the input.size(1). subset: https://w3id.org/aio/LayerSubset synonym: "LazyInstanceNorm3D" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/LeakyReLULayer name: LeakyReLU Layer def: "An activation layer that applies the leaky rectified linear unit function element-wise." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/LeakyReLU] comment: Leaky version of a Rectified Linear Unit. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ActivationLayer ! Activation Layer [Term] id: https://w3id.org/aio/LeastsquaresAnalysis name: Least-squares Analysis def: "A regression analysis which approximates the solution of overdetermined systems by minimizing the sum of the squares of the residuals." [https://en.wikipedia.org/wiki/Least_squares] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/LifelongLearningLLM name: Lifelong Learning LLM def: "A large language model that continually acquires new knowledge over time without forgetting previously learned information maintaining a balance between plasticity and stability." [] subset: https://w3id.org/aio/ModelSubset synonym: "Catastrophic forgetting" RELATED [] synonym: "Continual Learning LLM" EXACT [] synonym: "Forever Learning" EXACT [] synonym: "Plasticity-Stability balance" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/LinearFunction name: Linear Function def: "An activation function that has the form f(x) = a + bx." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/linear] subset: https://w3id.org/aio/FunctionSubset is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/LinearRegression name: Linear Regression def: "A regression analysis model that is a linear approach for modeling the relationship between a scalar response and one or more explanatory variables." [https://en.wikipedia.org/wiki/Linear_regression] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/LinkingBias name: Linking Bias def: "A use and interpretation bias arising when network attributes obtained from user connections activities or interactions misrepresent true user behavior." [https://doi.org/10.6028/NIST.SP.1270] comment: Bias arising when network attributes obtained from user connections, activities, or interactions misrepresent true user behavior. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/UseAndInterpretationBias ! Use And Interpretation Bias [Term] id: https://w3id.org/aio/LiquidStateMachineNetwork name: Liquid State Machine Network def: "A network that is a type of reservoir computer turning time-varying input into spatio-temporal activation patterns." [https://en.wikipedia.org/wiki/Liquid_state_machine] comment: Layers: Input, Spiking Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "LSM" EXACT [] is_a: https://w3id.org/aio/Network ! Network relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer relationship: BFO:0000051 https://w3id.org/aio/SpikingHiddenLayer ! has part Spiking Hidden Layer [Term] id: https://w3id.org/aio/LocalResponseNormLayer name: LocalResponseNorm Layer def: "A normalization layer that applies local response normalization over an input signal composed of several input planes." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies local response normalization over an input signal composed of several input planes, where channels occupy the second dimension. subset: https://w3id.org/aio/LayerSubset synonym: "LocalResponseNorm" EXACT [] is_a: https://w3id.org/aio/NormalizationLayer ! Normalization Layer [Term] id: https://w3id.org/aio/LocallyConnected1DLayer name: LocallyConnected1D Layer def: "A locally-connected layer for 1D inputs where each patch of the input is convolved with a different set of filters." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/LocallyConnected1D] comment: Locally-connected layer for 1D inputs. The LocallyConnected1D layer works similarly to the Conv1D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/LocallyconnectedLayer ! Locally-connected Layer [Term] id: https://w3id.org/aio/LocallyConnected2DLayer name: LocallyConnected2D Layer def: "A locally-connected layer for 2D inputs where each patch of the input is convolved with a different set of filters." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/LocallyConnected2D] comment: Locally-connected layer for 2D inputs. The LocallyConnected2D layer works similarly to the Conv2D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/LocallyconnectedLayer ! Locally-connected Layer [Term] id: https://w3id.org/aio/LocallyconnectedLayer name: Locally-connected Layer def: "A layer that works similarly to the Convolution1D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input." [https://faroit.com/keras-docs/1.2.2/layers/local/] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/LogisticRegression name: Logistic Regression def: "A regression analysis model that estimates the probability of an event occurring by modeling the log-odds of the event as a linear combination of one or more independent variables." [https://en.wikipedia.org/wiki/Logistic_regression] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/LongShortTermMemory name: Long Short Term Memory def: "A recurrent neural network with feedback connections that processes entire sequences of data." [https://en.wikipedia.org/wiki/Long_short-term_memory] comment: Layers: Input, Memory Cell, Output subset: https://w3id.org/aio/NetworkSubset synonym: "LSTM" EXACT [] is_a: https://w3id.org/aio/RecurrentNeuralNetwork ! Recurrent Neural Network relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/MemoryCellLayer ! has part Memory Cell Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/LossOfSituationalAwarenessBias name: Loss Of Situational Awareness Bias def: "An individual bias occurring when automation leads to humans being unaware of their situation making them unprepared to assume control in cooperative systems." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/LowResourceLLM name: Low-Resource LLM def: "A LLM which is optimized for performance in scenarios with limited data, computational resources, or for languages with sparse datasets." [] subset: https://w3id.org/aio/ModelSubset synonym: "Low-Resource Language Model" EXACT [] synonym: "low-resource languages" RELATED [] synonym: "resource-efficient" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/MachineLearning name: Machine Learning def: "A field of inquiry devoted to understanding and building methods that learn from data to improve performance on a set of tasks." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/MachineLearningSubset [Term] id: https://w3id.org/aio/ManifoldLearning name: Manifold Learning def: "A dimensionality reduction method based on the assumption that observed data lie on a low-dimensional manifold embedded in a higher-dimensional space." [https://arxiv.org/abs/2011.01307] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/DimensionalityReduction ! Dimensionality Reduction [Term] id: https://w3id.org/aio/MarkovChain name: Markov Chain def: "A network that is a stochastic model describing a sequence of possible events where the probability of each event depends only on the previous event's state." [https://en.wikipedia.org/wiki/Markov_chain] comment: Layers: Probalistic Hidden subset: https://w3id.org/aio/ModelSubset synonym: "Markov Process" EXACT [] synonym: "MC" EXACT [] synonym: "MP" EXACT [] is_a: https://w3id.org/aio/Network ! Network relationship: BFO:0000051 https://w3id.org/aio/ProbabilisticHiddenLayer ! has part Probabilistic Hidden Layer [Term] id: https://w3id.org/aio/MaskedLanguageModel name: Masked Language Model def: "A language model that is trained to predict randomly masked tokens in a sequence based on the remaining unmasked tokens allowing it to build deep bidirectional representations that can be effectively transferred to various NLP tasks via fine-tuning." [] subset: https://w3id.org/aio/ModelSubset synonym: "bidirectional encoder" RELATED [] synonym: "denoising autoencoder" RELATED [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/MaskingLayer name: Masking Layer def: "A layer that masks a sequence by using a mask value to skip timesteps." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Masking] comment: Masks a sequence by using a mask value to skip timesteps. For each timestep in the input tensor (dimension #1 in the tensor), if all values in the input tensor at that timestep are equal to mask_value, then the timestep will be masked (skipped) in all downstream layers (as long as they support masking). If any downstream layer does not support masking yet receives such an input mask, an exception will be raised. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/MatchedInputOutputLayer name: Matched Input-Output Layer def: "An input layer with a shape corresponding to that of the output layer." [] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/InputLayer ! Input Layer [Term] id: https://w3id.org/aio/MaxPooling1DLayer name: MaxPooling1D Layer def: "A pooling layer that performs max pooling operation for temporal data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool1D] comment: Max pooling operation for 1D temporal data. Downsamples the input representation by taking the maximum value over a spatial window of size pool_size. The window is shifted by strides. The resulting output, when using the "valid" padding option, has a shape of: output_shape = (input_shape - pool_size + 1) / strides) The resulting output shape when using the "same" padding option is: output_shape = input_shape / strides. subset: https://w3id.org/aio/LayerSubset synonym: "MaxPool1D" EXACT [] synonym: "MaxPooling1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/MaxPooling2DLayer name: MaxPooling2D Layer def: "A pooling layer that performs max pooling operation for spatial data." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool2D] comment: Max pooling operation for 2D spatial data. subset: https://w3id.org/aio/LayerSubset synonym: "MaxPool2D" EXACT [] synonym: "MaxPooling2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/MaxPooling3DLayer name: MaxPooling3D Layer def: "A pooling layer that performs max pooling operation for 3D data (spatial or spatio-temporal)." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool3D] comment: Max pooling operation for 3D data (spatial or spatio-temporal). Downsamples the input along its spatial dimensions (depth, height, and width) by taking the maximum value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension. subset: https://w3id.org/aio/LayerSubset synonym: "MaxPool3D" EXACT [] synonym: "MaxPooling3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/MaxUnpool1DLayer name: MaxUnpool1D Layer def: "A pooling layer that computes a partial inverse of MaxPool1D." [https://pytorch.org/docs/stable/nn.html#pooling-layers] comment: Computes a partial inverse of MaxPool1D. subset: https://w3id.org/aio/LayerSubset synonym: "MaxUnpool1D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/MaxUnpool2DLayer name: MaxUnpool2D Layer def: "A pooling layer that computes a partial inverse of MaxPool2D." [https://pytorch.org/docs/stable/nn.html#pooling-layers] comment: Computes a partial inverse of MaxPool2D. subset: https://w3id.org/aio/LayerSubset synonym: "MaxUnpool2D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/MaxUnpool3DLayer name: MaxUnpool3D Layer def: "A pooling layer that computes a partial inverse of MaxPool3D." [https://pytorch.org/docs/stable/nn.html#pooling-layers] comment: Computes a partial inverse of MaxPool3D. subset: https://w3id.org/aio/LayerSubset synonym: "MaxUnpool3D" EXACT [] is_a: https://w3id.org/aio/PoolingLayer ! Pooling Layer [Term] id: https://w3id.org/aio/MaximumLayer name: Maximum Layer def: "A merging layer that computes the maximum (element-wise) of a list of inputs." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Maximum] comment: Layer that computes the maximum (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/MergingLayer ! Merging Layer [Term] id: https://w3id.org/aio/MeasurementBias name: Measurement Bias def: "A selection and sampling bias arising when features and labels are proxies for desired quantities potentially leading to differential performance." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/MemoryAugmentedLLM name: Memory-Augmented LLM def: "A LLM which incorporates external writable and readable memory components, allowing it to store and retrieve information over long contexts." [https://arxiv.org/abs/2306.07174] subset: https://w3id.org/aio/ModelSubset synonym: "external memory" RELATED [] synonym: "Memory-Augmented Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/MemoryCellLayer name: Memory Cell Layer def: "A layer of cells, each with an internal state or weights." [https://doi.org/10.1162/neco.1997.9.8.1735] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/MergingLayer name: Merging Layer def: "A layer used to merge a list of inputs." [https://www.tutorialspoint.com/keras/keras_merge_layer.htm] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/MetaLearning name: Meta-Learning def: "A machine learning that automatically learns from metadata about machine learning experiments." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/MetaLearningLLM name: Meta-Learning LLM def: "A LLM which is trained in a way that allows it to quickly adapt to new tasks or datasets through only a few examples or fine-tuning steps, leveraging meta-learned priors about how to efficiently learn." [] subset: https://w3id.org/aio/ModelSubset synonym: "few-shot adaptation" RELATED [] synonym: "learning to learn" RELATED [] synonym: "Meta-Learning Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/MetricLearning name: Metric Learning def: "A deep neural network that learns a representation function mapping objects into an embedded space." [https://paperswithcode.com/task/metric-learning] comment: Learning a representation function that maps objects into an embedded space. subset: https://w3id.org/aio/NetworkSubset synonym: "Distance Metric Learning" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/MinimumLayer name: Minimum Layer def: "A merging layer that computes the minimum (element-wise) of a list of inputs." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Minimum] comment: Layer that computes the minimum (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/MergingLayer ! Merging Layer [Term] id: https://w3id.org/aio/MixtureofExpertsLLM name: Mixture-of-Experts LLM def: "A LLM which dynamically selects and combines outputs from multiple expert submodels, allowing for efficient scaling by conditionally activating only a subset of model components for each input." [https://proceedings.mlr.press/v162/du22c.html] subset: https://w3id.org/aio/ModelSubset synonym: "conditional computation" RELATED [] synonym: "Mixture-of-Experts Large Language Model" EXACT [] synonym: "model parallelism" RELATED [] synonym: "MoE Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ModeConfusionBias name: Mode Confusion Bias def: "A bias occurring when modal interfaces confuse human operators causing actions appropriate for a different mode but incorrect for the current situation." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/Model name: Model def: "An abstract representation of a complex system generally assembled as a set of logical mathematical or conceptual properties to simulate or understand the system's behavior." [https://en.wikipedia.org/wiki/Mathematical_model] subset: https://w3id.org/aio/ModelSubset [Term] id: https://w3id.org/aio/ModelEfficiency name: Model Efficiency def: "Techniques aimed at making models more efficient such as knowledge distillation." [https://doi.org/10.1145/3578938] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Computational Efficiency" EXACT [] synonym: "Model Optimization" EXACT [] is_a: https://w3id.org/aio/Preprocessing ! Preprocessing [Term] id: https://w3id.org/aio/ModelSelectionBias name: Model Selection Bias def: "A processing bias introduced when using data to select a single \"best\" model from many or when an explanatory variable has a weak relationship with the response variable." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/ProcessingBias ! Processing Bias [Term] id: https://w3id.org/aio/ModularLLM name: Modular LLM def: "A modular large language model that consists of multiple specialized components or skills that can be dynamically composed and recombined to solve complex tasks mimicking the modular structure of human cognition." [https://arxiv.org/abs/2302.11529v2] subset: https://w3id.org/aio/ModelSubset synonym: "component skills" RELATED [] synonym: "Modular Large Language Model" EXACT [] synonym: "skill composition" RELATED [] is_a: https://w3id.org/aio/ModularLanguageModel ! Modular Language Model [Term] id: https://w3id.org/aio/ModularLanguageModel name: Modular Language Model def: "A language model that consists of multiple specialized components or skills that can be dynamically composed and recombined to solve complex tasks mimicking the modular structure of human cognition." [https://arxiv.org/abs/2302.11529v2] subset: https://w3id.org/aio/ModelSubset synonym: "Modular LM" EXACT [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/MultiHeadAttentionLayer name: MultiHeadAttention Layer def: "An attention layer that allows the model to attend to information from different representation subspaces." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/MultiHeadAttention] comment: MultiHeadAttention layer. This is an implementation of multi-headed attention as described in the paper "Attention is all you Need" (Vaswani et al., 2017). If query, key, value are the same, then this is self-attention. Each timestep in query attends to the corresponding sequence in key, and returns a fixed-width vector.This layer first projects query, key and value. These are (effectively) a list of tensors of length num_attention_heads, where the corresponding shapes are (batch_size, , key_dim), (batch_size, , key_dim), (batch_size, , value_dim).Then, the query and key tensors are dot-producted and scaled. These are softmaxed to obtain attention probabilities. The value tensors are then interpolated by these probabilities, then concatenated back to a single tensor. Finally, the result tensor with the last dimension as value_dim can take an linear projection and return. When using MultiHeadAttention inside a custom Layer, the custom Layer must implement build() and call MultiHeadAttention's _build_from_signature(). This enables weights to be restored correctly when the model is loaded. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/AttentionLayer ! Attention Layer [Term] id: https://w3id.org/aio/MultiTaskLLM name: Multi-Task LLM def: "A LLM which is trained jointly on multiple language tasks simultaneously, learning shared representations that transfer across tasks." [] subset: https://w3id.org/aio/ModelSubset synonym: "Multi-Task Large Language Model" EXACT [] synonym: "transfer learning" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/MulticlassClassification name: Multiclass Classification def: "A machine learning task focused on methods that classify instances into one of three or more classes." [https://en.wikipedia.org/wiki/Multiclass_classification] comment: Methods that classify instances into one of three or more classes. subset: https://w3id.org/aio/MachineLearningSubset synonym: "Multinomial Classification" EXACT [] is_a: https://w3id.org/aio/Classification ! Classification [Term] id: https://w3id.org/aio/MultidimensionalScaling name: Multidimensional Scaling def: "A dimensionality reduction method that translates information about the pairwise distances among a set of objects or individuals into a configuration of points mapped into an abstract Cartesian space." [https://en.wikipedia.org/wiki/Multidimensional_scaling] subset: https://w3id.org/aio/MachineLearningSubset synonym: "MDS" EXACT [] is_a: https://w3id.org/aio/DimensionalityReduction ! Dimensionality Reduction [Term] id: https://w3id.org/aio/MultilingualLLM name: Multilingual LLM def: "A large language model that is trained on text from multiple languages learning shared representations that enable zero-shot or few-shot transfer to new languages." [] subset: https://w3id.org/aio/ModelSubset synonym: "cross-lingual transfer" RELATED [] synonym: "Multilingual Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/MultimodalDeepLearning name: Multimodal Deep Learning def: "A deep neural network that processes and links information using various modalities." [https://arxiv.org/abs/2105.11087] comment: Creating models that process and link information using various modalities. subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/MultimodalFusionLLM name: Multimodal Fusion LLM def: "A large language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation." [] subset: https://w3id.org/aio/ModelSubset synonym: "cross-modal grounding" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/MultimodalLLM name: Multimodal LLM def: "A multimodal large language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation." [https://arxiv.org/abs/2303.17580] subset: https://w3id.org/aio/ModelSubset synonym: "cross-modal grounding" RELATED [] synonym: "Multimodal Large Language Model" EXACT [] is_a: https://w3id.org/aio/MultimodalLanguageModel ! Multimodal Language Model [Term] id: https://w3id.org/aio/MultimodalLanguageModel name: Multimodal Language Model def: "A language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation." [https://arxiv.org/abs/2205.12630] subset: https://w3id.org/aio/ModelSubset synonym: "Mulimodal LM" EXACT [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/MultimodalLearning name: Multimodal Learning def: "A type of machine learning that uses multiple modalities of data such as text audio and images to improve learning outcomes." [https://doi.org/10.6028/NIST.SP.1270] comment: A type of deep learning that uses multiple modalities of data, such as text, audio, and images, to improve learning outcomes. subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/MultimodalPromptbasedLanguageModel name: Multimodal Prompt-based Language Model def: "A multimodal LLM which processes prompts that include multiple modalities, such as both text and images, to generate relevant responses." [https://arxiv.org/abs/2210.03094] subset: https://w3id.org/aio/ModelSubset is_a: https://w3id.org/aio/MultimodalLanguageModel ! Multimodal Language Model [Term] id: https://w3id.org/aio/MultimodalTransformer name: Multimodal Transformer def: "A transformer network that processes and relates information from different modalities such as text images and audio using a shared embedding space and attention mechanism to learn joint representations across modalities." [] subset: https://w3id.org/aio/ModelSubset synonym: "unified encoder" RELATED [] synonym: "vision-language model" RELATED [] is_a: https://w3id.org/aio/TransformerNetwork ! Transformer Network [Term] id: https://w3id.org/aio/MultiplyLayer name: Multiply Layer def: "A merging layer that multiplies (element-wise) a list of inputs." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Multiply] comment: Layer that multiplies (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/MergingLayer ! Merging Layer [Term] id: https://w3id.org/aio/NaturalLanguageProcessing name: Natural Language Processing def: "A subfield of machine learning focused on the interactions between computers and human language including programming computers to process and analyze large amounts of natural language data." [https://en.wikipedia.org/wiki/Natural_language_processing] subset: https://w3id.org/aio/MachineLearningSubset synonym: "NLP" EXACT [] is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/Network name: Network def: "A system of interconnected nodes or entities for communication computation or data exchange." [] subset: https://w3id.org/aio/ClassSubset [Term] id: https://w3id.org/aio/NeuralTuringMachineNetwork name: Neural Turing Machine Network def: "A deep feedforward network that combines neural network pattern matching with the algorithmic power of programmable computers." [https://en.wikipedia.org/wiki/Neural_Turing_machine] comment: Layers: Input, Hidden, Spiking Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "NTM" EXACT [] is_a: https://w3id.org/aio/DeepFeedForwardNetwork ! Deep Feed-Forward Network is_a: https://w3id.org/aio/LongShortTermMemory ! Long Short Term Memory relationship: BFO:0000051 https://w3id.org/aio/SpikingHiddenLayer ! has part Spiking Hidden Layer [Term] id: https://w3id.org/aio/NeuroSymbolicLLM name: Neuro-Symbolic LLM def: "A LLM which combines neural language modeling with symbolic reasoning components, leveraging structured knowledge representations and logical inferences to improve reasoning capabilities." [] subset: https://w3id.org/aio/ModelSubset synonym: "knowledge reasoning" RELATED [] synonym: "Neuro-Symbolic Large Language Model" EXACT [] synonym: "symbolic grounding" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/NoiseDenseLayer name: Noise Dense Layer def: "A layer that is a densely-connected neural network layer with added noise for regularization." [https://www.tensorflow.org/addons/api_docs/python/tfa/layers/NoisyDense] comment: Noisy dense layer that injects random noise to the weights of dense layer. Noisy dense layers are fully connected layers whose weights and biases are augmented by factorised Gaussian noise. The factorised Gaussian noise is controlled through gradient descent by a second weights layer. A NoisyDense layer implements the operation: $$ mathrm\{NoisyDense\}(x) = mathrm\{activation\}(mathrm\{dot\}(x, mu + (sigma cdot epsilon)) mathrm\{bias\}) $$ where mu is the standard weights layer, epsilon is the factorised Gaussian noise, and delta is a second weights layer which controls epsilon. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/NoisyInputLayer name: Noisy Input Layer def: "An input layer that adds noise to each value." [https://doi.org/10.1109/21.155944] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/InputLayer ! Input Layer [Term] id: https://w3id.org/aio/Normalization name: Normalization def: "The technique of transforming data into a standard format or scale typically to reduce redundancy and improve consistency often involving the adjustment of values measured on different scales to a common scale." [] subset: https://w3id.org/aio/PreprocessingSubset is_a: https://w3id.org/aio/DataPreparation ! Data Preparation [Term] id: https://w3id.org/aio/NormalizationLayer name: Normalization Layer def: "A preprocessing layer that normalizes continuous features." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Normalization] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/NumericalFeaturesPreprocessingLayer ! Numerical Features Preprocessing Layer [Term] id: https://w3id.org/aio/NumericalFeaturesPreprocessingLayer name: Numerical Features Preprocessing Layer def: "A layer that performs numerical data preprocessing operations." [https://keras.io/guides/preprocessing_layers/] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/OneshotLearning name: One-shot Learning def: "A deep neural network that classified objects from one or only a few examples." [https://en.wikipedia.org/wiki/One-shot_learning] subset: https://w3id.org/aio/NetworkSubset synonym: "OSL" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/OrdinalLLM name: Ordinal LLM def: "A large language model that is trained to model ordinal relationships and rank outputs rather than model probability distributions over text sequences directly." [] subset: https://w3id.org/aio/ModelSubset synonym: "Ordinal Large Language Model" EXACT [] synonym: "preference modeling" RELATED [] synonym: "ranking" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/OutputLayer name: Output Layer def: "A layer containing the last neurons in the network that produces given outputs for the program." [https://www.techopedia.com/definition/33263/output-layer-neural-networks] comment: The output layer in an artificial neural network is the last layer of neurons that produces given outputs for the program. Though they are made much like other artificial neurons in the neural network, output layer neurons may be built or observed in a different way, given that they are the last “actor” nodes on the network. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/PReLULayer name: PReLU Layer def: "An activation layer that applies parametric rectified linear unit function element-wise." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/PReLU] comment: Parametric Rectified Linear Unit. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ActivationLayer ! Activation Layer [Term] id: https://w3id.org/aio/Perceptron name: Perceptron def: "An artificial neural network with a supervised learning algorithm for binary classification using a linear predictor function." [] comment: Layers: Input, Output subset: https://w3id.org/aio/NetworkSubset synonym: "Feed-Forward Network" EXACT [] synonym: "FFN" EXACT [] synonym: "Single Layer Perceptron" EXACT [] synonym: "SLP" EXACT [] is_a: https://w3id.org/aio/ArtificialNeuralNetwork ! Artificial Neural Network relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/PermuteLayer name: Permute Layer def: "A layer that permutes the dimensions of the input according to a given pattern." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Permute] comment: Permutes the dimensions of the input according to a given pattern. Useful e.g. connecting RNNs and convnets. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/PersonalizedLLM name: Personalized LLM def: "A large language model that adapts its language modeling and generation to the preferences style and persona of individual users or audiences." [] subset: https://w3id.org/aio/ModelSubset synonym: "Personalized Large Language Model" EXACT [] synonym: "user adaptation LLM" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/PolicyLayer name: Policy Layer def: "A layer that, after taking a set of states or values as input, predicts a probability distribution of actions to take." [] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/PoolingLayer name: Pooling Layer def: "A layer that serves to mitigate the sensitivity of convolutional layers to location and spatially downsample representations." [https://d2l.ai/chapter_convolutional-neural-networks/pooling.html] comment: Pooling layers serve the dual purposes of mitigating the sensitivity of convolutional layers to location and of spatially downsampling representations. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/PopularityBias name: Popularity Bias def: "A selection and sampling bias where more popular items are more exposed under-representing less popular items." [https://doi.org/10.6028/NIST.SP.1270] comment: Selection bias where more popular items are more exposed, under-representing less popular items. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/PopulationBias name: Population Bias def: "A selection and sampling bias characterized by systematic distortions in demographics or other user characteristics between represented users and the target population." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/Preprocessing name: Preprocessing def: "The series of steps applied to raw data before it is used in a machine learning model including tasks such as normalization scaling encoding and transformation to ensure the data is in an appropriate format and quality for analysis." [https://doi.org/10.1109/ICDE.2019.00245] subset: https://w3id.org/aio/PreprocessingSubset [Term] id: https://w3id.org/aio/PreprocessingLayer name: Preprocessing Layer def: "A layer that performs data preprocessing operations." [https://www.tensorflow.org/guide/keras/preprocessing_layers] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/PresentationBias name: Presentation Bias def: "An individual bias arising from how information is presented on the Web via a user interface due to rating or ranking of output or through users' self-selected biased interaction." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/PrincipalComponentAnalysis name: Principal Component Analysis def: "A dimensionality reduction method for analyzing large datasets with high-dimensional features per observation increasing data interpretability while preserving maximum information and enabling visualization." [https://en.wikipedia.org/wiki/Principal_component_analysis] subset: https://w3id.org/aio/MachineLearningSubset synonym: "PCA" EXACT [] is_a: https://w3id.org/aio/DimensionalityReduction ! Dimensionality Reduction [Term] id: https://w3id.org/aio/ProbabilisticGraphicalModel name: Probabilistic Graphical Model def: "A machine learning model in which a graph expresses the conditional dependence structure between random variables." [https://en.wikipedia.org/wiki/Graphical_model] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Graphical Model" EXACT [] synonym: "PGM" EXACT [] synonym: "Structure Probabilistic Model" EXACT [] is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/ProbabilisticHiddenLayer name: Probabilistic Hidden Layer def: "A hidden layer that estimates the probability of a sample being within a certain category." [] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/HiddenLayer ! Hidden Layer [Term] id: https://w3id.org/aio/ProbabilisticTopicModel name: Probabilistic Topic Model def: "A probabilistic graphical model that uses statistical techniques to analyze the words in each text to discover common themes their connections and their changes over time." [https://pyro.ai/examples/prodlda.html] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/ProbabilisticGraphicalModel ! Probabilistic Graphical Model [Term] id: https://w3id.org/aio/ProcessingBias name: Processing Bias def: "A computational bias resulting from judgment modulated by affect influenced by the level of efficacy and efficiency in information processing." [https://en.wikipedia.org/wiki/Bias_(statistics)] comment: Judgment modulated by affect, influenced by the level of efficacy and efficiency in information processing; often referred to as aesthetic judgment in cognitive sciences. subset: https://w3id.org/aio/BiasSubset synonym: "Validation Bias" EXACT [] is_a: https://w3id.org/aio/ComputationalBias ! Computational Bias [Term] id: https://w3id.org/aio/PromptbasedFineTuningLLM name: Prompt-based Fine-Tuning LLM def: "A LLM which is fine-tuned on a small number of examples or prompts, rather than full task datasets. This allows for rapid adaptation to new tasks with limited data, leveraging the model's few-shot learning capabilities." [] subset: https://w3id.org/aio/ModelSubset synonym: "few-shot learning" RELATED [] synonym: "in-context learning" RELATED [] synonym: "Prompt-based Fine-Tuning Large Language Model" EXACT [] synonym: "Prompt-tuned Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ProportionalHazardsModel name: Proportional Hazards Model def: "A regression analysis method for survival analysis where the unique effect of a unit increase in a covariate is multiplicative with respect to the hazard rate." [https://en.wikipedia.org/wiki/Proportional_hazards_model] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis is_a: https://w3id.org/aio/SurvivalAnalysis ! Survival Analysis [Term] id: https://w3id.org/aio/RNNLayer name: RNN Layer def: "The base class for recurrent layers." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RNN] comment: Base class for recurrent layers. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RecurrentLayer ! Recurrent Layer [Term] id: https://w3id.org/aio/RadialBasisNetwork name: Radial Basis Network def: "A deep feedforward network that uses radial basis functions as activation functions for pattern recognition and interpolation." [https://en.wikipedia.org/wiki/Radial_basis_function_network] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "Radial Basis Function Network" EXACT [] synonym: "RBFN" EXACT [] synonym: "RBN" EXACT [] is_a: https://w3id.org/aio/DeepFeedForwardNetwork ! Deep Feed-Forward Network [Term] id: https://w3id.org/aio/RandomBrightnessLayer name: RandomBrightness Layer def: "An image preprocessing layer that randomly adjusts brightness during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomBrightness] comment: A preprocessing layer which randomly adjusts brightness during training. This layer will randomly increase/reduce the brightness for the input RGB images. At inference time, the output will be identical to the input. Call the layer with training=True to adjust the brightness of the input. Note that different brightness adjustment factors will be apply to each the images in the batch. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RandomContrastLayer name: RandomContrast Layer def: "An image preprocessing layer that randomly adjusts contrast during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomContrast] comment: A preprocessing layer which randomly adjusts contrast during training. This layer will randomly adjust the contrast of an image or images by a random factor. Contrast is adjusted independently for each channel of each image during training. For each channel, this layer computes the mean of the image pixels in the channel and then adjusts each component x of each pixel to (x - mean) * contrast_factor + mean. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and in integer or floating point dtype. By default, the layer will output floats. The output value will be clipped to the range [0, 255], the valid range of RGB colors. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RandomCropLayer name: RandomCrop Layer def: "An image preprocessing layer that randomly crops images during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomCrop] comment: A preprocessing layer which randomly crops images during training. During training, this layer will randomly choose a location to crop images down to a target size. The layer will crop all the images in the same batch to the same cropping location. At inference time, and during training if an input image is smaller than the target size, the input will be resized and cropped so as to return the largest possible window in the image that matches the target aspect ratio. If you need to apply random cropping at inference time, set training to True when calling the layer. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RandomEffectsModel name: Random Effects Model def: "A regression analysis model where the model parameters are random variables." [https://en.wikipedia.org/wiki/Random_effects_model] subset: https://w3id.org/aio/MachineLearningSubset synonym: "REM" EXACT [] is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/RandomFlipLayer name: RandomFlip Layer def: "An image preprocessing layer that randomly flips images during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomFlip] comment: A preprocessing layer which randomly flips images during training. This layer will flip the images horizontally and or vertically based on the mode attribute. During inference time, the output will be identical to input. Call the layer with training=True to flip the input. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RandomForest name: Random Forest def: "An ensemble learning method for classification regression and other tasks that constructs a multitude of decision trees during training." [https://en.wikipedia.org/wiki/Random_forest] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/EnsembleLearning ! Ensemble Learning [Term] id: https://w3id.org/aio/RandomHeightLayer name: RandomHeight Layer def: "An image preprocessing layer that randomly varies image height during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomHeight] comment: A preprocessing layer which randomly varies image height during training. This layer adjusts the height of a batch of images by a random factor. The input should be a 3D (unbatched) or 4D (batched) tensor in the "channels_last" image data format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. By default, this layer is inactive during inference. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RandomRotationLayer name: RandomRotation Layer def: "An image preprocessing layer that randomly rotates images during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomRotation] comment: A preprocessing layer which randomly rotates images during training. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RandomTranslationLayer name: RandomTranslation Layer def: "An image preprocessing layer that randomly translates images during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomTranslation] comment: A preprocessing layer which randomly translates images during training. This layer will apply random translations to each image during training, filling empty space according to fill_mode. aInput pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RandomWidthLayer name: RandomWidth Layer def: "An image preprocessing layer that randomly varies image width during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomWidth] comment: A preprocessing layer which randomly varies image width during training. This layer will randomly adjusts the width of a batch of images of a batch of images by a random factor. The input should be a 3D (unbatched) or 4D (batched) tensor in the "channels_last" image data format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. By default, this layer is inactive during inference. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RandomZoomLayer name: RandomZoom Layer def: "An image preprocessing layer that randomly zooms in or out on images during training." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomZoom] comment: A preprocessing layer which randomly zooms images during training. This layer will randomly zoom in or out on each axis of an image independently, filling empty space according to fill_mode.Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RankingBias name: Ranking Bias def: "An anchoring bias characterized by the idea that top-ranked results are the most relevant and important leading to more clicks than other results." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/AnchoringBias ! Anchoring Bias [Term] id: https://w3id.org/aio/RashomonEffectBias name: Rashomon Effect Bias def: "An individual bias characterized by differences in perspective memory recall interpretation and reporting of the same event by multiple persons or witnesses." [https://doi.org/10.6028/NIST.SP.1270] comment: Differences in perspective, memory, recall, interpretation, and reporting of the same event by multiple persons or witnesses. subset: https://w3id.org/aio/BiasSubset synonym: "Rashomon Effect" EXACT [] synonym: "Rashomon Principle" EXACT [] is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/ReLUFunction name: ReLU Function def: "An activation function that returns max(x 0) the element-wise maximum of 0 and the input tensor." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/relu] comment: The ReLU activation function returns: max(x, 0), the element-wise maximum of 0 and the input tensor. subset: https://w3id.org/aio/FunctionSubset synonym: "Rectified Linear Unit" EXACT [] synonym: "ReLU" EXACT [] is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/ReLULayer name: ReLU Layer def: "An activation layer that applies the rectified linear unit function element-wise." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ReLU] comment: Rectified Linear Unit activation function. With default values, it returns element-wise max(x, 0). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ActivationLayer ! Activation Layer [Term] id: https://w3id.org/aio/ReasoningLLM name: Reasoning LLM def: "A large language model that incorporates explicit reasoning capabilities leveraging logical rules axioms or external knowledge to make deductive inferences during language tasks." [https://doi.org/10.18653/v1/2023.acl-long.347] subset: https://w3id.org/aio/ModelSubset synonym: "logical inferences" RELATED [] synonym: "Rational Large Language Model" EXACT [] synonym: "reasoning" RELATED [] synonym: "Reasoning Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/RecurrentLayer name: Recurrent Layer def: "A layer composed of recurrent units with the number equal to the hidden size of the layer." [https://docs.nvidia.com/deepLearning/performance/dl-performance-recurrent/index.html#recurrent-layer] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/RecurrentNeuralNetwork name: Recurrent Neural Network def: "A deep neural network with connections forming a directed graph along a temporal sequence enabling dynamic behavior." [] subset: https://w3id.org/aio/NetworkSubset synonym: "RecNN" EXACT [] synonym: "Recurrent Network" EXACT [] synonym: "RN" EXACT [] is_a: https://w3id.org/aio/Network ! Network [Term] id: https://w3id.org/aio/RecursiveLLM name: Recursive LLM def: "A large language model that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving systematic generalization abilities." [https://doi.org/10.1609/aaai.v33i01.33017450] subset: https://w3id.org/aio/ModelSubset synonym: "iterative refinement" RELATED [] synonym: "Recursive Large Language Model" EXACT [] synonym: "Self-Attending Large Language Model" EXACT [] synonym: "self-attention" RELATED [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/RecursiveLanguageModel name: Recursive Language Model def: "A language model that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving systematic generalization abilities." [https://en.wikipedia.org/wiki/Recurrent_neural_network] comment: Layers: Input, Memory Cell, Output subset: https://w3id.org/aio/ModelSubset synonym: "Compositional generalization" RELATED [] synonym: "RLM" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/MemoryCellLayer ! has part Memory Cell Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/RecursiveNeuralNetwork name: Recursive Neural Network def: "A deep neural network that recursively applies weights over structured input to generate structured or scalar predictions." [https://en.wikipedia.org/wiki/Recursive_neural_network] subset: https://w3id.org/aio/NetworkSubset synonym: "RecuNN" EXACT [] synonym: "RvNN" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/RegressionAnalysis name: Regression Analysis def: "A set of statistical processes for estimating the relationships between a dependent variable and one or more independent variables." [https://en.wikipedia.org/wiki/Regression_analysis] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Regression analysis" EXACT [] synonym: "Regression model" EXACT [] is_a: https://w3id.org/aio/SupervisedLearning ! Supervised Learning [Term] id: https://w3id.org/aio/RegularizationLayer name: Regularization Layer def: "A layer that applies penalties on layer parameters or layer activity during optimization summed into the loss function that the network optimizes." [https://keras.io/api/layers/regularizers/] comment: Regularizers allow you to apply penalties on layer parameters or layer activity during optimization. These penalties are summed into the loss function that the network optimizes. Regularization penalties are applied on a per-layer basis. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/ReinforcementLearning name: Reinforcement Learning def: "A type of machine learning focused on methods that do not require labeled input/output pairs or explicit correction of sub-optimal actions focusing instead on balancing exploration and exploitation to optimize performance over time." [https://en.wikipedia.org/wiki/Reinforcement_learning] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/ReinforcementLearningLLM name: Reinforcement Learning LLM def: "A large language model that is fine-tuned using reinforcement learning where the model receives rewards for generating text that satisfies certain desired properties or objectives improving the quality safety or alignment of generated text." [] comment: An RL-LLM is a language model fine-tuned using reinforcement learning, where the model receives rewards for generating text that satisfies certain desired properties or objectives. This can improve the quality, safety, or alignment of generated text. subset: https://w3id.org/aio/ModelSubset synonym: "decision transformers" RELATED [] synonym: "Reinforcement Learning Large Language Model" EXACT [] synonym: "reward modeling" RELATED [] synonym: "RL-Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/RepeatVectorLayer name: RepeatVector Layer def: "A layer that repeats the input n times." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/RepeatVector] comment: Repeats the input n times. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/RepresentationBias name: Representation Bias def: "A selection and sampling bias due to non-random sampling of subgroups making trends non-generalizable to new populations." [https://doi.org/10.6028/NIST.SP.1270] comment: Bias due to non-random sampling of subgroups, making trends non-generalizable to new populations. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/RepresentationLearning name: Representation Learning def: "A deep neural network that discovers representations required for feature detection or classification from raw data." [https://en.wikipedia.org/wiki/Feature_learning] comment: Discovering representations required for feature detection or classification from raw data. subset: https://w3id.org/aio/NetworkSubset synonym: "Feature Learning" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/RescalingLayer name: Rescaling Layer def: "A preprocessing layer that rescales input values to a new range." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Rescaling] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ImagePreprocessingLayer ! Image Preprocessing Layer [Term] id: https://w3id.org/aio/ReshapeLayer name: Reshape Layer def: "A layer that reshapes the inputs into the given shape." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Reshape] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/ReshapingLayer name: Reshaping Layer def: "A layer that is used to change the shape of the input." [https://keras.io/api/layers/reshaping_layers/reshape/] comment: Reshape layers are used to change the shape of the input. subset: https://w3id.org/aio/LayerSubset synonym: "Reshape Layer" EXACT [] is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/ResidualNeuralNetwork name: Residual Neural Network def: "A deep neural network that employs skip connections to bypass layers facilitating learning of residual functions." [https://en.wikipedia.org/wiki/Residual_neural_network] comment: Layers: Input, Weight, BN, ReLU, Weight, BN, Addition, ReLU subset: https://w3id.org/aio/NetworkSubset synonym: "Deep Residual Network" EXACT [] synonym: "DRN" EXACT [] synonym: "ResNet" EXACT [] synonym: "ResNN" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network relationship: BFO:0000051 https://w3id.org/aio/AdditionLayer ! has part Addition Layer relationship: BFO:0000051 https://w3id.org/aio/BatchNormalizationLayer ! has part BatchNormalization Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/ReLULayer ! has part ReLU Layer relationship: BFO:0000051 https://w3id.org/aio/WeightedLayer ! has part Weighted Layer [Term] id: https://w3id.org/aio/ResizingLayer name: Resizing Layer def: "A preprocessing layer that resizes images to a target size." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Resizing] comment: A preprocessing layer which resizes images. This layer resizes an image input to a target height and width. The input should be a 4D (batched) or 3D (unbatched) tensor in "channels_last" format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. This layer can be called on tf.RaggedTensor batches of input images of distinct sizes, and will resize the outputs to dense tensors of uniform size. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ImagePreprocessingLayer ! Image Preprocessing Layer [Term] id: https://w3id.org/aio/RestrictedBoltzmannMachine name: Restricted Boltzmann Machine def: "A Boltzmann machine network that learns the probability distribution of its input data." [https://en.wikipedia.org/wiki/Restricted_Boltzmann_machine] comment: Layers: Backfed Input, Probabilistic Hidden subset: https://w3id.org/aio/NetworkSubset synonym: "RBM" EXACT [] is_a: https://w3id.org/aio/BoltzmannMachineNetwork ! Boltzmann Machine Network [Term] id: https://w3id.org/aio/RetrievalAugmentedLLM name: Retrieval-Augmented LLM def: "A LLM which combines a pre-trained language model with a retrieval system that can access external knowledge sources. This allows the model to condition its generation on relevant retrieved knowledge, improving factual accuracy and knowledge grounding." [] subset: https://w3id.org/aio/ModelSubset synonym: "knowledge grounding" RELATED [] synonym: "open-book question answering" RELATED [] synonym: "Retrieval-Augmented Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/RidgeRegression name: Ridge Regression def: "A regression analysis method that estimates the coefficients of multiple regression models in scenarios where the independent variables are highly correlated." [https://en.wikipedia.org/wiki/Ridge_regression] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/SELUFunction name: SELU Function def: "An activation function that multiplies scale (> 1) with the output of the ELU function to ensure a slope larger than one for positive inputs." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/selu] subset: https://w3id.org/aio/FunctionSubset synonym: "Scaled Exponential Linear Unit" EXACT [] synonym: "SELU" EXACT [] is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/SeasonalAutoregressiveIntegratedMovingAverage name: Seasonal Autoregressive Integrated Moving-Average def: "A model that extends ARIMA, explicitly supporting univariate time series data with a seasonal component, combining seasonal differencing with ARIMA modeling." [] subset: https://w3id.org/aio/ModelSubset synonym: "SARIMA" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/SelectionAndSamplingBias name: Selection And Sampling Bias def: "A computational bias introduced by non-random selection of individuals groups or data failing to ensure representativeness." [https://doi.org/10.6028/NIST.SP.1270] comment: Bias introduced by non-random selection of individuals, groups, or data, failing to ensure representativeness. subset: https://w3id.org/aio/BiasSubset synonym: "Sampling Bias" EXACT [] synonym: "Selection Bias" EXACT [] synonym: "Selection Effect" EXACT [] is_a: https://w3id.org/aio/ComputationalBias ! Computational Bias [Term] id: https://w3id.org/aio/SelectiveAdherenceBias name: Selective Adherence Bias def: "An individual bias characterized by the tendency to selectively adopt algorithmic advice that matches pre-existing beliefs and stereotypes." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/SelfSupervisedLLM name: Self-Supervised LLM def: "A LLM which learns rich representations by solving pretext tasks that involve predicting parts of the input from other observed parts of the data, without relying on human-annotated labels." [] subset: https://w3id.org/aio/ModelSubset synonym: "Pretext tasks" RELATED [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/SelfsupervisedLearning name: Self-supervised Learning def: "A machine learning that is intermediate between supervised and unsupervised learning and predicts parts of the input data from other observed parts without relying on human-annotated labels." [https://en.wikipedia.org/wiki/Self-supervised_learning] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/SemiSupervisedLLM name: Semi-Supervised LLM def: "A LLM which combines self-supervised pretraining on unlabeled data with supervised fine-tuning on labeled task data." [] subset: https://w3id.org/aio/ModelSubset synonym: "self-training" RELATED [] synonym: "Semi-Supervised Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/SeparableConvolution1DLayer name: SeparableConvolution1D Layer def: "A layer that performs depthwise separable 1D convolution." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv1D] comment: Depthwise separable 1D convolution. This layer performs a depthwise convolution that acts separately on channels, followed by a pointwise convolution that mixes channels. If use_bias is True and a bias initializer is provided, it adds a bias vector to the output. It then optionally applies an activation function to produce the final output.a subset: https://w3id.org/aio/LayerSubset synonym: "SeparableConv1D Layer" EXACT [] is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/SeparableConvolution2DLayer name: SeparableConvolution2D Layer def: "A layer that performs depthwise separable 2D convolution." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv2D] comment: Depthwise separable 2D convolution. Separable convolutions consist of first performing a depthwise spatial convolution (which acts on each input channel separately) followed by a pointwise convolution which mixes the resulting output channels. The depth_multiplier argument controls how many output channels are generated per input channel in the depthwise step. Intuitively, separable convolutions can be understood as a way to factorize a convolution kernel into two smaller kernels, or as an extreme version of an Inception block. subset: https://w3id.org/aio/LayerSubset synonym: "SeparableConv2D Layer" EXACT [] is_a: https://w3id.org/aio/ConvolutionalLayer ! Convolutional Layer [Term] id: https://w3id.org/aio/SigmoidFunction name: Sigmoid Function def: "An activation function that applies the sigmoid activation function sigmoid(x) = 1 / (1 + exp(-x)) always returning a value between 0 and 1." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/sigmoid] comment: Applies the sigmoid activation function sigmoid(x) = 1 / (1 + exp(-x)). For small values (<-5), sigmoid returns a value close to zero, and for large values (>5) the result of the function gets close to 1. Sigmoid is equivalent to a 2-element Softmax, where the second element is assumed to be zero. The sigmoid function always returns a value between 0 and 1. subset: https://w3id.org/aio/FunctionSubset is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/SimpleRNNCellLayer name: SimpleRNNCell Layer def: "A layer that processes one step within the whole time sequence input for a SimpleRNN layer." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/SimpleRNNCell] comment: Cell class for SimpleRNN. This class processes one step within the whole time sequence input, whereas tf.keras.layer.SimpleRNN processes the whole sequence. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/SimpleRNNLayer name: SimpleRNN Layer def: "A recurrent layer that implements a fully-connected RNN where the output is to be fed back to input." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/SimpleRNN] comment: Fully-connected RNN where the output is to be fed back to input. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RecurrentLayer ! Recurrent Layer [Term] id: https://w3id.org/aio/SimponsParadoxBias name: Simpon's Paradox Bias def: "Ahere the association between two variables changes when controlling for another variable." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Simpson's Paradox" EXACT [] is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/SocietalBias name: Societal Bias def: "A bias characterized by being for or against groups or individuals based on social identities demographic factors or immutable physical characteristics often manifesting as stereotypes." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/Bias ! Bias [Term] id: https://w3id.org/aio/SoftmaxFunction name: Softmax Function def: "An activation function where the elements of the output vector are in range (0 1) and sum to 1 and each vector is handled independently." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/softmax] comment: The elements of the output vector are in range (0, 1) and sum to 1. Each vector is handled independently. The axis argument sets which axis of the input the function is applied along. Softmax is often used as the activation for the last layer of a classification network because the result could be interpreted as a probability distribution. The softmax of each vector x is computed as exp(x) / tf.reduce_sum(exp(x)). The input values in are the log-odds of the resulting probability. subset: https://w3id.org/aio/FunctionSubset is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/SoftmaxLayer name: Softmax Layer def: "An activation layer that applies the softmax function to the inputs." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Softmax] comment: Softmax activation function. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ActivationLayer ! Activation Layer [Term] id: https://w3id.org/aio/SoftplusFunction name: Softplus Function def: "An activation function that is softplus(x) = log(exp(x) + 1)." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/softplus] comment: softplus(x) = log(exp(x) + 1) subset: https://w3id.org/aio/FunctionSubset is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/SoftsignFunction name: Softsign Function def: "An activation function that is softsign(x) = x / (abs(x) + 1)." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/softsign] comment: softsign(x) = x / (abs(x) + 1) subset: https://w3id.org/aio/FunctionSubset is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/SparseAutoEncoder name: Sparse Auto Encoder def: "An autoencoder network with more hidden units than inputs that constrains only a few hidden units to be active at once." [] comment: Layers: Input, Hidden, Matched Output-Input subset: https://w3id.org/aio/NetworkSubset synonym: "SAE" EXACT [] synonym: "Sparse AE" EXACT [] synonym: "Sparse Autoencoder" EXACT [] is_a: https://w3id.org/aio/AutoEncoderNetwork ! Auto Encoder Network [Term] id: https://w3id.org/aio/SparseLLM name: Sparse LLM def: "A large language model that uses techniques like pruning or quantization to reduce the number of non-zero parameters in the model making it more parameter-efficient and easier to deploy on resource-constrained devices." [] subset: https://w3id.org/aio/ModelSubset synonym: "model compression" RELATED [] synonym: "parameter efficiency" RELATED [] synonym: "Sparse Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/SparseLearning name: Sparse Learning def: "A representation learning network that finds sparse representations of input data as a linear combination of basic elements and identifies those elements." [https://en.wikipedia.org/wiki/Sparse_dictionary_learning] subset: https://w3id.org/aio/NetworkSubset synonym: "Sparse coding" EXACT [] synonym: "Sparse dictionary Learning" EXACT [] is_a: https://w3id.org/aio/RepresentationLearning ! Representation Learning [Term] id: https://w3id.org/aio/SpatialDropout1DLayer name: SpatialDropout1D Layer def: "A regularization layer that performs the same function as Dropout but drops entire 1D feature maps instead of individual elements." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout1D] comment: Spatial 1D version of Dropout. This version performs the same function as Dropout, however, it drops entire 1D feature maps instead of individual elements. If adjacent frames within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout1D will help promote independence between feature maps and should be used instead. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RegularizationLayer ! Regularization Layer [Term] id: https://w3id.org/aio/SpatialDropout2DLayer name: SpatialDropout2D Layer def: "A regularization layer that performs the same function as Dropout but drops entire 2D feature maps instead of individual elements." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout2D] comment: Spatial 2D version of Dropout. This version performs the same function as Dropout, however, it drops entire 2D feature maps instead of individual elements. If adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout2D will help promote independence between feature maps and should be used instead.a subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RegularizationLayer ! Regularization Layer [Term] id: https://w3id.org/aio/SpatialDropout3DLayer name: SpatialDropout3D Layer def: "A regularization layer that performs the same function as Dropout but drops entire 3D feature maps instead of individual elements." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout3D] comment: Spatial 3D version of Dropout. This version performs the same function as Dropout, however, it drops entire 3D feature maps instead of individual elements. If adjacent voxels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout3D will help promote independence between feature maps and should be used instead. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RegularizationLayer ! Regularization Layer [Term] id: https://w3id.org/aio/SpatialRegression name: Spatial Regression def: "A regression analysis method used to model spatial relationships." [https://gisgeography.com/spatial-regression-models-arcgis/] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/RegressionAnalysis ! Regression Analysis [Term] id: https://w3id.org/aio/SpikingHiddenLayer name: Spiking Hidden Layer def: "A hidden layer that makes connections to an additional, heterogeneous hidden layer; modeled after biological neural networks." [https://doi.org/10.1016/S0893-6080(97)00011-7] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/HiddenLayer ! Hidden Layer [Term] id: https://w3id.org/aio/StackedRNNCellsLayer name: StackedRNNCells Layer def: "A layer that allows a stack of RNN cells to behave as a single cell." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/StackedRNNCells] comment: Wrapper allowing a stack of RNN cells to behave as a single cell. Used to implement efficient stacked RNNs. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/StreetlightEffectBias name: Streetlight Effect Bias def: "An individual bias where people search only where it is easiest to look." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Streetlight Effect" EXACT [] is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/StringLookupLayer name: StringLookup Layer def: "A categorical features preprocessing layer that maps string features to integer indices." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/StringLookup] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/CategoricalFeaturesPreprocessingLayer ! Categorical Features Preprocessing Layer [Term] id: https://w3id.org/aio/SubtractLayer name: Subtract Layer def: "A merging layer that subtracts two inputs." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Subtract] comment: Layer that subtracts two inputs. It takes as input a list of tensors of size 2, both of the same shape, and returns a single tensor, (inputs[0] - inputs[1]), also of the same shape. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/MergingLayer ! Merging Layer [Term] id: https://w3id.org/aio/SubwordSegmentation name: Subword Segmentation def: "The process of dividing text into subword units which are smaller than words but larger than individual characters to improve the efficiency and effectiveness of natural language processing models by capturing meaningful subunits of words." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Byte Pair Encoding" RELATED [] synonym: "Fragmentation" EXACT [] synonym: "Part-word Division" EXACT [] synonym: "SentencePiece" RELATED [] is_a: https://w3id.org/aio/DataPreparation ! Data Preparation [Term] id: https://w3id.org/aio/SunkCostFallacyBias name: Sunk Cost Fallacy Bias def: "A bias characterized by the tendency to continue an endeavor due to previously invested resources despite costs outweighing benefits." [https://doi.org/10.6028/NIST.SP.1270] comment: The tendency to continue an endeavor due to previously invested resources, despite costs outweighing benefits. subset: https://w3id.org/aio/BiasSubset synonym: "Sunk Cost Fallacy" EXACT [] is_a: https://w3id.org/aio/Bias ! Bias [Term] id: https://w3id.org/aio/SupervisedBiclustering name: Supervised Biclustering def: "A biclustering task focused on methods that simultaneously cluster the rows and columns of a labeled matrix considering data labels to enhance cluster coherence." [https://en.wikipedia.org/wiki/Biclustering] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Supervised Block Clustering" EXACT [] synonym: "Supervised Co-clustering" EXACT [] synonym: "Supervised Joint Clustering" EXACT [] synonym: "Supervised Two-mode Clustering" EXACT [] synonym: "Supervised Two-way Clustering" EXACT [] is_a: https://w3id.org/aio/Biclustering ! Biclustering [Term] id: https://w3id.org/aio/SupervisedClustering name: Supervised Clustering def: "A clustering task focused on methods that group labeled objects such that objects in the same group have similar labels relative to those in other groups." [https://en.wikipedia.org/wiki/Cluster_analysis] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Cluster analysis" EXACT [] is_a: https://w3id.org/aio/Clustering ! Clustering [Term] id: https://w3id.org/aio/SupervisedLearning name: Supervised Learning def: "A type of machine learning focused on methods that learn a function mapping input to output based on example input-output pairs." [https://en.wikipedia.org/wiki/Supervised_learning] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/SupportVectorMachine name: Support Vector Machine def: "A network with supervised learning models for classification and regression that maps training examples to points in space maximizing the gap between categories." [https://en.wikipedia.org/wiki/Support-vector_machine] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "Supper Vector Network" EXACT [] synonym: "SVM" EXACT [] synonym: "SVN" EXACT [] is_a: https://w3id.org/aio/Network ! Network relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/SurvivalAnalysis name: Survival Analysis def: "A machine learning task focused on methods for analyzing the expected duration of time until one or more events occur such as death in biological organisms or failure in mechanical systems." [https://en.wikipedia.org/wiki/Survival_analysis] subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/SurvivorshipBias name: Survivorship Bias def: "A processing bias characterized by the tendency to focus on items observations or people that \"survive\" a selection process overlooking those that did not." [https://doi.org/10.6028/NIST.SP.1270] comment: The tendency to focus on items, observations, or people that "survive" a selection process, overlooking those that did not. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/ProcessingBias ! Processing Bias [Term] id: https://w3id.org/aio/SwishFunction name: Swish Function def: "An activation function that is x*sigmoid(x) a smooth non-monotonic function that consistently matches or outperforms ReLU on deep networks." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/swish] comment: x*sigmoid(x). It is a smooth, non-monotonic function that consistently matches or outperforms ReLU on deep networks, it is unbounded above and bounded below. subset: https://w3id.org/aio/FunctionSubset is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/SymmetricallyConnectedNetwork name: Symmetrically Connected Network def: "A network that is a type of recurrent neural network where connections between units are symmetrical with equal weights in both directions." [https://ieeexplore.ieee.org/document/287176] comment: Symmetrically connected networks are a type of recurrent neural network where connections between units are symmetrical, meaning they have equal weights in both directions. This structure allows the network to maintain consistent information flow and equilibrium. subset: https://w3id.org/aio/NetworkSubset synonym: "SCN" EXACT [] is_a: https://w3id.org/aio/Network ! Network [Term] id: https://w3id.org/aio/SyncBatchNormLayer name: SyncBatchNorm Layer def: "A batch normalization layer that applies synchronous Batch Normalization across multiple devices." [https://pytorch.org/docs/stable/nn.html#normalization-layers] comment: Applies Batch Normalization over a N-Dimensional input (a mini-batch of [N-2]D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift . subset: https://w3id.org/aio/LayerSubset synonym: "SyncBatchNorm" EXACT [] is_a: https://w3id.org/aio/BatchNormalizationLayer ! BatchNormalization Layer [Term] id: https://w3id.org/aio/SystemicBias name: Systemic Bias def: "A bias resulting from procedures and practices of institutions that operate in ways which result in certain social groups being advantaged or favored and others being disadvantaged or devalued." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset synonym: "Institutional Bias" EXACT [] synonym: "Societal Bias" EXACT [] is_a: https://w3id.org/aio/Bias ! Bias [Term] id: https://w3id.org/aio/TanhFunction name: Tanh Function def: "An activation function that is the hyperbolic tangent activation function." [https://www.tensorflow.org/api_docs/python/tf/keras/activations/tanh] comment: Hyperbolic tangent activation function. subset: https://w3id.org/aio/FunctionSubset synonym: "hyperbolic tangent" EXACT [] is_a: https://w3id.org/aio/Function ! Function [Term] id: https://w3id.org/aio/TemporalBias name: Temporal Bias def: "A selection and sampling bias arising from differences in populations and behaviors over time." [https://doi.org/10.6028/NIST.SP.1270] subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/TextPreprocessingLayer name: Text Preprocessing Layer def: "A layer that performs text data preprocessing operations." [https://keras.io/guides/preprocessing_layers/] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/TextVectorizationLayer name: TextVectorization Layer def: "A preprocessing layer that maps text features to integer sequences." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/TextVectorization] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/TextPreprocessingLayer ! Text Preprocessing Layer [Term] id: https://w3id.org/aio/ThresholdAutoregressive name: Threshold Autoregressive def: "A model that allows for different autoregressive processes depending on the regime or state of the time series, enabling the capture of nonlinear behaviors." [] subset: https://w3id.org/aio/ModelSubset synonym: "TAR" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/ThresholdedReLULayer name: ThresholdedReLU Layer def: "An activation layer that applies the thresholded rectified linear unit function element-wise." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ThresholdedReLU] comment: Thresholded Rectified Linear Unit. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ActivationLayer ! Activation Layer [Term] id: https://w3id.org/aio/TimeDistributedLayer name: TimeDistributed Layer def: "A wrapper layer that applies a layer to every temporal slice of an input." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/TimeDistributed] comment: This wrapper allows to apply a layer to every temporal slice of an input. Every input should be at least 3D, and the dimension of index one of the first input will be considered to be the temporal dimension. Consider a batch of 32 video samples, where each sample is a 128x128 RGB image with channels_last data format, across 10 timesteps. The batch input shape is (32, 10, 128, 128, 3). You can then use TimeDistributed to apply the same Conv2D layer to each of the 10 timesteps, independently: subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RecurrentLayer ! Recurrent Layer [Term] id: https://w3id.org/aio/TimeSeriesAnalysis name: Time Series Analysis def: "A machine learning task focused on methods for analyzing time series data to extract meaningful statistics and characteristics." [https://en.wikipedia.org/wiki/Time_series] comment: Methods for analyzing time series data to extract meaningful statistics and characteristics. subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/TimeSeriesForecasting name: Time Series Forecasting def: "A machine learning task focused on methods that predict future values based on previously observed values." [https://en.wikipedia.org/wiki/Time_series] comment: Methods that predict future values based on previously observed values. subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/Tokenization name: Tokenization def: "The process of converting a sequence of text into smaller meaningful units called tokens typically words or subwords for the purpose of analysis or processing by language models." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Lexical Analysis" EXACT [] synonym: "Text Segmentation" EXACT [] is_a: https://w3id.org/aio/DataPreparation ! Data Preparation [Term] id: https://w3id.org/aio/TrainingStrategies name: Training Strategies def: "The methodologies and approaches used to train machine learning models including techniques such as supervised learning unsupervised learning reinforcement learning and transfer learning aimed at optimizing model performance." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Instructional Methods" EXACT [] synonym: "Learning Techniques" EXACT [] is_a: https://w3id.org/aio/Preprocessing ! Preprocessing [Term] id: https://w3id.org/aio/TransferLearning name: Transfer Learning def: "A type of machine learning focused on methods that reuse or transfer information from previously learned tasks to facilitate the learning of new tasks." [https://en.wikipedia.org/wiki/Transfer_learning] subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/TransferLearningLLM name: Transfer Learning LLM def: "A large language model that leverages knowledge acquired during training on one task to improve performance on different but related tasks facilitating more efficient learning and adaptation." [] subset: https://w3id.org/aio/ModelSubset synonym: "transfer learning" RELATED [] synonym: "Transfer LLM" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/TransformerLLM name: Transformer LLM def: "A transformer language model with large training corpuses and sets of parameters that uses the transformer architecture based on multi-head attention mechanisms allowing it to contextualize tokens within a context window for effective language understanding and generation." [https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture)] subset: https://w3id.org/aio/ModelSubset synonym: "Transformer Large Language Model" EXACT [] is_a: https://w3id.org/aio/TransformerLanguageModel ! Transformer Language Model [Term] id: https://w3id.org/aio/TransformerLanguageModel name: Transformer Language Model def: "A language model that uses the transformer architecture based on multi-head attention mechanisms allowing it to contextualize tokens within a context window for effective language understanding and generation." [https://arxiv.org/abs/1706.03762] subset: https://w3id.org/aio/ModelSubset synonym: "Transformer LM" EXACT [] is_a: https://w3id.org/aio/LanguageModel ! Language Model [Term] id: https://w3id.org/aio/TransformerNetwork name: Transformer Network def: "A deep neural network that utilizes attention mechanisms to weigh the significance of input data." [https://en.wikipedia.org/wiki/Transformer_(machine_Learning_model)] comment: A transformer network utilizes attention mechanisms to weigh the significance of each part of the input data, widely used in natural language processing (NLP) and computer vision (CV). subset: https://w3id.org/aio/NetworkSubset is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/UncertaintyBias name: Uncertainty Bias def: "A selection and sampling bias favoring groups better represented in training data due to less prediction uncertainty." [https://doi.org/10.6028/NIST.SP.1270] comment: Bias favoring groups better represented in training data, due to less prediction uncertainty. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/SelectionAndSamplingBias ! Selection And Sampling Bias [Term] id: https://w3id.org/aio/UnitNormalizationLayer name: UnitNormalization Layer def: "A normalization layer that normalizes a batch of inputs so that each input in the batch has a L2 norm equal to 1." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/UnitNormalization] comment: Unit normalization layer. Normalize a batch of inputs so that each input in the batch has a L2 norm equal to 1 (across the axes specified in axis). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/RecurrentLayer ! Recurrent Layer [Term] id: https://w3id.org/aio/UnsupervisedBiclustering name: Unsupervised Biclustering def: "A biclustering task focused on methods that simultaneously cluster the rows and columns of an unlabeled input matrix to identify submatrices with coherent patterns." [https://en.wikipedia.org/wiki/Biclustering] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Block Clustering" EXACT [] synonym: "Co-clustering" EXACT [] synonym: "Joint Clustering" EXACT [] synonym: "Two-mode Clustering" EXACT [] synonym: "Two-way Clustering" EXACT [] is_a: https://w3id.org/aio/Biclustering ! Biclustering [Term] id: https://w3id.org/aio/UnsupervisedClustering name: Unsupervised Clustering def: "A clustering task focused on methods that group a set of unlabeled objects such that objects in the same group are more similar to each other than to those in other groups." [https://en.wikipedia.org/wiki/Cluster_analysis] subset: https://w3id.org/aio/MachineLearningSubset synonym: "Cluster analysis" EXACT [] is_a: https://w3id.org/aio/Clustering ! Clustering [Term] id: https://w3id.org/aio/UnsupervisedLLM name: Unsupervised LLM def: "A large language model that is trained solely on unlabeled data using self-supervised objectives like masked language modeling without any supervised fine-tuning." [] subset: https://w3id.org/aio/ModelSubset synonym: "self-supervised" RELATED [] synonym: "Unsupervised Large Language Model" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/UnsupervisedLearning name: Unsupervised Learning def: "A type of machine learning focused on algorithms that learn patterns from unlabeled data." [https://en.wikipedia.org/wiki/Unsupervised_learning] comment: Algorithms that learn patterns from unlabeled data. subset: https://w3id.org/aio/MachineLearningSubset is_a: https://w3id.org/aio/MachineLearning ! Machine Learning [Term] id: https://w3id.org/aio/UnsupervisedPretrainedNetwork name: Unsupervised Pretrained Network def: "A network that initializes a discriminative neural net from one trained using an unsupervised criterion." [https://metacademy.org/graphs/concepts/unsupervised_pre_training] comment: Unsupervised pre-training initializes a discriminative neural net from one trained using an unsupervised criterion, aiding in optimization and overfitting issues. subset: https://w3id.org/aio/NetworkSubset synonym: "UPN" EXACT [] is_a: https://w3id.org/aio/Network ! Network [Term] id: https://w3id.org/aio/UpSampling1DLayer name: UpSampling1D Layer def: "A layer that upsamples the input by repeating each temporal step size times along the time axis." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling1D] comment: Upsampling layer for 1D inputs. Repeats each temporal step size times along the time axis. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/UpSampling2DLayer name: UpSampling2D Layer def: "A layer that upsamples the input by repeating each row and column size times." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling2D] comment: Upsampling layer for 2D inputs. Repeats the rows and columns of the data by size[0] and size[1] respectively. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/UpSampling3DLayer name: UpSampling3D Layer def: "A layer that upsamples the input by repeating each depth" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling3D] comment: Upsampling layer for 3D inputs. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/UseAndInterpretationBias name: Use And Interpretation Bias def: "A computational bias characterized by inappropriately analyzing ambiguous stimuli scenarios and events." [https://doi.org/10.6028/NIST.SP.1270] comment: Bias inappropriately analyzing ambiguous stimuli, scenarios, and events. subset: https://w3id.org/aio/BiasSubset synonym: "Interpretive Bias" EXACT [] is_a: https://w3id.org/aio/ComputationalBias ! Computational Bias [Term] id: https://w3id.org/aio/UserInteractionBias name: User Interaction Bias def: "An individual bias arising when a user imposes their own biases during interaction with data output results etc." [https://doi.org/10.6028/NIST.SP.1270] comment: Bias arising when a user imposes their own biases during interaction with data, output, results, etc. subset: https://w3id.org/aio/BiasSubset is_a: https://w3id.org/aio/IndividualBias ! Individual Bias [Term] id: https://w3id.org/aio/VariationalAutoEncoder name: Variational Auto Encoder def: "An autoencoder network that imposes a probabilistic structure on the latent space for unsupervised learning." [] comment: Layers: Input, Probabilistic Hidden, Matched Output-Input subset: https://w3id.org/aio/NetworkSubset synonym: "VAE" EXACT [] is_a: https://w3id.org/aio/AutoEncoderNetwork ! Auto Encoder Network relationship: BFO:0000051 https://w3id.org/aio/ProbabilisticHiddenLayer ! has part Probabilistic Hidden Layer [Term] id: https://w3id.org/aio/VectorAutoregression name: Vector Autoregression def: "A model that captures the linear interdependencies among multiple time series, where each variable is modeled as a linear function of its own past values and the past values of all other variables in the system." [] subset: https://w3id.org/aio/ModelSubset synonym: "VAR" EXACT [] is_a: https://w3id.org/aio/Model ! Model [Term] id: https://w3id.org/aio/VocabularyReduction name: Vocabulary Reduction def: "The technique of limiting the number of unique tokens in a language model's vocabulary by merging or eliminating less frequent tokens thereby optimizing computational efficiency and resource usage." [] subset: https://w3id.org/aio/PreprocessingSubset synonym: "Lexical Simplification" EXACT [] synonym: "Lexicon Pruning" EXACT [] synonym: "Vocabulary Condensation" EXACT [] is_a: https://w3id.org/aio/DataPreparation ! Data Preparation [Term] id: https://w3id.org/aio/WeightedLayer name: Weighted Layer def: "A layer of values to be applied to other cells or neurons in a network." [] subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/WrapperLayer name: Wrapper Layer def: "An abstract base class for wrappers that augment the functionality of another layer." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/Wrapper] comment: Abstract wrapper base class. Wrappers take another layer and augment it in various ways. Do not use this class as a layer, it is only an abstract base class. Two usable wrappers are the TimeDistributed and Bidirectional wrappers. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/Layer ! Layer [Term] id: https://w3id.org/aio/ZeroPadding1DLayer name: ZeroPadding1D Layer def: "A layer that zero-pads the input along the time axis." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding1D] comment: Zero-padding layer for 1D input (e.g. temporal sequence). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/ZeroPadding2DLayer name: ZeroPadding2D Layer def: "A layer that zero-pads the input along the height and width dimensions." [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding2D] comment: Zero-padding layer for 2D input (e.g. picture). This layer can add rows and columns of zeros at the top, bottom, left and right side of an image tensor. subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/ZeroPadding3DLayer name: ZeroPadding3D Layer def: "A layer that zero-pads the input along the depth" [https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding3D] comment: Zero-padding layer for 3D data (spatial or spatio-temporal). subset: https://w3id.org/aio/LayerSubset is_a: https://w3id.org/aio/ReshapingLayer ! Reshaping Layer [Term] id: https://w3id.org/aio/ZeroShotLearningLLM name: Zero-Shot Learning LLM def: "A LLM which performs tasks or understands concepts it has not explicitly been trained on, demonstrating a high degree of generalization and understanding." [] subset: https://w3id.org/aio/ModelSubset synonym: "zero-shot learning" RELATED [] synonym: "Zero-Shot LLM" EXACT [] is_a: https://w3id.org/aio/LargeLanguageModel ! Large Language Model [Term] id: https://w3id.org/aio/ZeroshotLearning name: Zero-shot Learning def: "A deep neural network that predicts classes at test time from classes not observed during training." [https://en.wikipedia.org/wiki/Zero-shot_learning] subset: https://w3id.org/aio/NetworkSubset synonym: "ZSL" EXACT [] is_a: https://w3id.org/aio/DeepNeuralNetwork ! Deep Neural Network [Term] id: https://w3id.org/aio/node2vec name: node2vec def: "A machine learning designed to learn continuous feature representations for nodes in a graph by optimizing a neighborhood-preserving objective." [https://en.wikipedia.org/wiki/Node2vec] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "N2V" EXACT [] is_a: https://w3id.org/aio/MachineLearning ! Machine Learning relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/node2vecCBOW name: node2vec-CBOW def: "A node2vec that predicts the current node from a window of surrounding context nodes, with the order of context nodes not influencing prediction." [https://en.wikipedia.org/wiki/Word2vec] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "CBOW" RELATED [] synonym: "N2V-CBOW" EXACT [] is_a: https://w3id.org/aio/word2vec ! word2vec [Term] id: https://w3id.org/aio/node2vecSkipGram name: node2vec-SkipGram def: "A node2vec that uses the current node to predict the surrounding window of context nodes, weighing nearby context nodes more heavily than distant ones." [https://en.wikipedia.org/wiki/Word2vec] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "N2V-SkipGram" EXACT [] synonym: "SkipGram" RELATED [] is_a: https://w3id.org/aio/node2vec ! node2vec [Term] id: https://w3id.org/aio/tDistributedStochasticNeighborembedding name: t-Distributed Stochastic Neighbor embedding def: "A dimensionality reduction for visualizing high-dimensional data by giving each datapoint a location in a two or three-dimensional map." [https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding] subset: https://w3id.org/aio/MachineLearningSubset synonym: "t-SNE" EXACT [] synonym: "tSNE" EXACT [] is_a: https://w3id.org/aio/DimensionalityReduction ! Dimensionality Reduction [Term] id: https://w3id.org/aio/word2vec name: word2vec def: "A machine learning that generates distributed representations of words by training a shallow neural network model, which aims to predict the context of each word within a corpus. This algorithm captures semantic meanings of words through their contextual usage in the text." [https://en.wikipedia.org/wiki/Word2vec] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "W2V" EXACT [] is_a: https://w3id.org/aio/MachineLearning ! Machine Learning relationship: BFO:0000051 https://w3id.org/aio/HiddenLayer ! has part Hidden Layer relationship: BFO:0000051 https://w3id.org/aio/InputLayer ! has part Input Layer relationship: BFO:0000051 https://w3id.org/aio/OutputLayer ! has part Output Layer [Term] id: https://w3id.org/aio/word2vecCBOW name: word2vec-CBOW def: "A word2vec that predicts the current word from a window of surrounding context words, ignoring the order of context words." [https://en.wikipedia.org/wiki/Word2vec] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "CBOW" RELATED [] synonym: "W2V-CBOW" EXACT [] is_a: https://w3id.org/aio/word2vec ! word2vec [Term] id: https://w3id.org/aio/word2vecSkipGram name: word2vec-SkipGram def: "A word2vec that predicts surrounding context words from the current word, giving more weight to nearby context words than distant ones." [https://en.wikipedia.org/wiki/Word2vec] comment: Layers: Input, Hidden, Output subset: https://w3id.org/aio/NetworkSubset synonym: "SkipGram" RELATED [] synonym: "W2V-SkipGram" EXACT [] is_a: https://w3id.org/aio/word2vec ! word2vec [Typedef] id: BFO:0000050 name: part of def: "A core relation that holds between a part and its whole" [] [Typedef] id: BFO:0000051 name: has part def: "A core relation that holds between a whole and its part" []