{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Index.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8wN5BpUKYFHA",
        "colab_type": "text"
      },
      "source": [
        "# Deep Learning with Tensorflow 2.0"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fwY_CgcMYFAr",
        "colab_type": "text"
      },
      "source": [
        "![Img](https://raw.githubusercontent.com/adhiraiyan/DeepLearningWithTF2.0/master/logo/DLBookCover2.png)\n",
        "\n",
        "A practical guide to [Deep Learning with Tensorflow 2.0](https://www.adhiraiyan.org/DeepLearningWithTensorflow.html) by Mukesh Mithrakumar. \n",
        "The content is available [on GitHub](https://github.com/adhiraiyan/DeepLearningWithTF2.0) and you can run it in [Google Colaboratory](https://colab.research.google.com/github/adhiraiyan/DeepLearningWithTF2.0/blob/master/notebooks/Index.ipynb) as well. The code is released under the [MIT license](https://opensource.org/licenses/MIT)\n",
        "\n",
        "---"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "w0FfjM53YE4C",
        "colab_type": "text"
      },
      "source": [
        "# Table of Contents\n",
        "\n",
        "## [1. Introduction](01.00-Introduction.ipynb)\n",
        "- 01.01 Who should read this book\n",
        "- 01.02 Historical Trends in Deep Learning\n",
        "\n",
        "## [2. Linear Algebra](02.00-Linear-Algebra.ipynb)\n",
        "- 02.01 Scalars, Vectors, Matrices and Tensors\n",
        "- 02.02 Multiplying Matrices and Vectors\n",
        "- 02.03 Identity and Inverse Matrices\n",
        "- 02.04 Linear Dependence and Span\n",
        "- 02.05 Norms\n",
        "- 02.06 Special Kinds of Matrices and Vectors\n",
        "- 02.07 Eigendecomposition\n",
        "- 02.08 Singular Value Decomposition\n",
        "- 02.09 The Moore-Penrose Pseudoinverse\n",
        "- 02.10 The Trace Operator\n",
        "- 02.11 The Determinant\n",
        "- 02.12 Example: Principal Components Analysis\n",
        "\n",
        "\n",
        "## [3. Probability and Information Theory](03.00-Probability-and-Information-Theory.ipynb)\n",
        "- 03.01 Why Probability?\n",
        "- 03.02 Random Variables\n",
        "- 03.03 Probability Distributions\n",
        "- 03.04 Marginal Probability\n",
        "- 03.05 Conditional Probability\n",
        "- 03.06 The Chain Rule of Conditional Probabilities\n",
        "- 03.07 Independence and Conditional Independence\n",
        "- 03.08 Expectation, Variance and Covariance\n",
        "- 03.09 Common Probability Distributions\n",
        "- 03.10 Useful Properties of Common Functions\n",
        "- 03.11 Bayes' Rule\n",
        "- 03.12 Technical Details of Continuous Variables\n",
        "- 03.13 Information Theory\n",
        "- 03.14 Structured Probabilistic Models\n",
        "\n",
        "\n",
        "## [4. Numerical Computation](04.00-Numerical-Computation.ipynb)\n",
        "- 04.01 Overflow and Underflow\n",
        "- 04.02 Poor Conditioning\n",
        "- 04.03 Gradient-Based Optimization\n",
        "- 04.04 Constrained Optimization\n",
        "- 04.05 Example: Linear Least Squares\n",
        "\n",
        "\n",
        "## [5. Machine Learning Basics](05.00-Machine-Learning-Basics.ipynb)\n",
        "- 05.01 Learning Algorithms\n",
        "- 05.02 Capacity, Overfitting and Underfitting\n",
        "- 05.03 Hyperparameters and Validation Sets\n",
        "- 05.04 Estimators, Bias and Variance\n",
        "- 05.05 Maximum Likelihood Estimation\n",
        "- 05.06 Bayesian Statistics\n",
        "- 05.07 Supervised Learning Algorithms\n",
        "- 05.08 Unsupervised Learning Algorithms\n",
        "- 05.09 Stochastic Gradient Descent\n",
        "- 05.10 Building a Machine Learning Algorithm\n",
        "- 05.11 Challenges Motivating Deep Learning\n",
        "\n",
        "\n",
        "## [6. Deep Feedforward Networks](06.00-Deep-Feedforward-Networks.ipynb)\n",
        "- 06.01 Example: Learning XOR\n",
        "- 06.02 Gradient-Based Learning\n",
        "- 06.03 Hidden Units\n",
        "- 06.04 Architecture Design\n",
        "- 06.05 Back-Propagation and Other Differentiation Algorithms\n",
        "- 06.06 Historical Notes\n",
        "\n",
        "\n",
        "## [7. Regularization for Deep Learning](07.00-Regularization-for-Deep-Learning.ipynb)\n",
        "- 07.01 Parameter Norm Penalties\n",
        "- 07.02 Norm Penalties as Constrained Optimization\n",
        "- 07.03 Regularization and Under-Constrained Problems\n",
        "- 07.04 Dataset Augmentation\n",
        "- 07.05 Noise Robustness\n",
        "- 07.06 Semi-Supervised Learning\n",
        "- 07.07 Multitask Learning\n",
        "- 07.08 Early Stopping\n",
        "- 07.09 Parameter Tying and Parameter Sharing\n",
        "- 07.10 Sparse Representations\n",
        "- 07.11 Bagging and Other Ensemble Methods\n",
        "- 07.12 Dropout\n",
        "- 07.13 Adversarial Training\n",
        "- 07.14 Tangent Distance, Tangent Prop and Manifold Tangent Classifier\n",
        "\n",
        "\n",
        "## [8. Optimization for Training Deep Models](08.00-Optimization-for-Training-Deep-Models.ipynb)\n",
        "- 08.01 How Learning Differs from Pure Optimization\n",
        "- 08.02 Challenges in Neural Network Optimization\n",
        "- 08.03 Basic Algorithms\n",
        "- 08.04 Parameter Initialization Strategies\n",
        "- 08.05 Algorithms with Adaptive Learning Rates\n",
        "- 08.06 Approximate Second-Order Methods\n",
        "- 08.07 Optimization Strategies and Meta-Algorithms\n",
        "\n",
        "\n",
        "## [9. Convolutional Networks](09.00-Convolutional-Networks.ipynb)\n",
        "- 09.01 The Convolution Operation\n",
        "- 09.02 Motivation\n",
        "- 09.03 Pooling\n",
        "- 09.04 Convolution and Pooling as an Infinitely Strong Prior\n",
        "- 09.05 Variants of the Basic Convolution Function\n",
        "- 09.06 Structured Outputs\n",
        "- 09.07 Data Types\n",
        "- 09.08 Efficient Convolution Algorithms\n",
        "- 09.09 Random or Unsupervised Features\n",
        "- 09.10 The Neuroscientific Basis for Convolutional Networks\n",
        "- 09.11 Convolutional Networks and the History of Deep Learning\n",
        "\n",
        "\n",
        "## [10. Sequence Modeling: Recurrent and Recursive Nets](10.00-Sequence-Modeling-Recurrent-and-Recursive-Nets.ipynb)\n",
        "- 10.01 Unfolding Computational Graphs\n",
        "- 10.02 Recurrent Neural Networks\n",
        "- 10.03 Bidirectional RNNs\n",
        "- 10.04 Encoder-Decoder Sequence-to-Sequence Architectures\n",
        "- 10.05 Deep Recurrent Networks\n",
        "- 10.06 Recursive Neural Networks\n",
        "- 10.07 The Challenge of Long-Term Dependencies\n",
        "- 10.08 Echo State Networks\n",
        "- 10.09 Leaky Units and Other Strategies for Multiple Time Scales\n",
        "- 10.10 The Long Short-Term Memory and Other Gated RNNs\n",
        "- 10.11 Optimization for Long-Term Dependencies\n",
        "- 10.12 Explicit Memory\n",
        "\n",
        "\n",
        "## [11. Practical Methodology](11.00-Practical-Methodology.ipynb)\n",
        "- 11.01 Performance Metrics\n",
        "- 11.02 Default Baseline Models\n",
        "- 11.03 Determining Whether to Gather More Data\n",
        "- 11.04 Selecting Hyperparameters\n",
        "- 11.05 Debugging Strategies\n",
        "- 11.06 Example: Multi-Digit Number Recognition\n",
        "\n",
        "\n",
        "## [12. Applications](12.00-Applications.ipynb)\n",
        "- 12.01 Large-Scale Deep Learning\n",
        "- 12.02 Computer Vision\n",
        "- 12.03 Speech Recognition\n",
        "- 12.04 Natural Language Processing\n",
        "- 12.05 Other Applications\n",
        "\n",
        "\n",
        "## [13. Linear Factor Models](13.00-Linear-Factor-Models.ipynb)\n",
        "- 13.01 Probabilistic PCA and Factor Analysis\n",
        "- 13.02 Independent Component Analysis\n",
        "- 13.03 Slow Feature Analysis\n",
        "- 13.04 Sparse Coding\n",
        "- 13.05 Manifold Interpretation of PCA\n",
        "\n",
        "\n",
        "## [14. Autoencoders](14.00-Autoencoders.ipynb)\n",
        "- 14.01 Undercomplete Autoencoders\n",
        "- 14.02 Regularized Autoencoders\n",
        "- 14.03 Representational Power, Layer Size and Depth\n",
        "- 14.04 Stochastic Encoders and Decoders\n",
        "- 14.05 Denoising Autoencoders\n",
        "- 14.06 Learning Manifolds with Autoencoders\n",
        "- 14.07 Contractive Autoencoders\n",
        "- 14.08 Predictive Sparse Decomposition\n",
        "- 14.09 Applications of Autoencoders\n",
        "\n",
        "\n",
        "## [15. Representation Learning](15.00-Representation-Learning.ipynb)\n",
        "- 15.01 Greedy Layer-Wise Unsupervised Pretraining\n",
        "- 15.02 Transfer Learning and Domain Adaptation\n",
        "- 15.03 Semi-Supervised Disentangling of Causal Factors\n",
        "- 15.04 Distributed Representation\n",
        "- 15.05 Exponential Gains from Depth\n",
        "- 15.06 Providing Clues to Discover Underlying Causes\n",
        "\n",
        "\n",
        "## [16. Structured Probabilistic Models for Deep Learning](16.00-Structured-Probabilistic-Models-for-Deep-Learning.ipynb)\n",
        "- 16.01 The Challenge of Unstructured Modeling\n",
        "- 16.02 Using Graphs to Describe Model Structure\n",
        "- 16.03 Sampling from Graphical Models\n",
        "- 16.04 Advantages of Structured Modeling\n",
        "- 16.05 Learning about Dependencies\n",
        "- 16.06 Inference and Approximate Inference\n",
        "- 16.07 The Deep Learning Approach to Structured Probabilistic Models\n",
        "\n",
        "\n",
        "## [17. Monte Carlo Methods](17.00-Monte-Carlo-Methods.ipynb)\n",
        "- 17.01 Sampling and Monte Carlo Methods\n",
        "- 17.02 Importance Sampling\n",
        "- 17.03 Markov Chain Monte Carlo Methods\n",
        "- 17.04 Gibbs Sampling\n",
        "- 17.05 The Challenge of Mixing between Separated Modes\n",
        "\n",
        "\n",
        "## [18. Confronting the Partition Function](18.00-Confronting-the-Partition-Function.ipynb)\n",
        "- 18.01 The Log-Likelihood Gradient\n",
        "- 18.02 Stochastic Maximum Likelihood and Contrastive Divergence\n",
        "- 18.03 Pseudolikelihood\n",
        "- 18.04 Score Matching and Ratio Matching\n",
        "- 18.05 Denoising Score Matching\n",
        "- 18.06 Noise-Contrastive Estimation\n",
        "- 18.07 Estimating the Partition Function\n",
        "\n",
        "\n",
        "## [19. Approximate Inference](19.00-Approximate-Inference.ipynb)\n",
        "- 19.01 Inference as Optimization\n",
        "- 19.02 Expectation Maximization\n",
        "- 19.03 MAP Inference and Sparse Coding\n",
        "- 19.04 Variational Inference and Learning\n",
        "- 19.05 Learned Approximate Inference\n",
        "\n",
        "\n",
        "## [20. Deep Generative Models](20.00-Deep-Generative-Models.ipynb)\n",
        "- 20.01 Boltzmann Machines\n",
        "- 20.02 Restricted Boltzmann Machines\n",
        "- 20.03 Deep Belief Networks\n",
        "- 20.04 Deep Boltzmann Machines\n",
        "- 20.05 Boltzmann Machines for Real-Valued Data\n",
        "- 20.06 Convolutional Boltzmann Machines\n",
        "- 20.07 Boltzmann Machines for Structured or Sequential Outputs\n",
        "- 20.08 Other Boltzmann Machines\n",
        "- 20.09 Back-Propagation through Random Operations\n",
        "- 20.10 Directed Generative Nets\n",
        "- 20.11 Drawing Samples from Autoencoders\n",
        "- 20.12 Generative Stochastic Networks\n",
        "- 20.13 Other Generation Schemes\n",
        "- 20.14 Evaluating Generative Models\n",
        "- 20.15 Conclusion"
      ]
    }
  ]
}