{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## SYDE556/750 Assignment 1: Representation in Populations of Neurons\n", "\n", "- Due Date: January 22rd at midnight\n", "- Total marks: 20 (20% of final grade)\n", "- Late penalty: 1 mark per day\n", "- It is recommended that you use a language with a matrix library and graphing capabilities. Two main suggestions are Python and MATLAB.\n", "- *Do not use or refer to any code from Nengo*" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 1) Representation of Scalars" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 1.1) Basic encoding and decoding\n", "\n", "Write a program that implements a neural representation of a scalar value $x$. For the neuron model, use a rectified linear neuron model ($a=max(J,0)$). Choose the maximum firing rates randomly (uniformly distributed between 100Hz and 200Hz at their highest value, which will either be at $x=1$ or at $x=-1$), and choose the x-intercepts randomly (uniformly distributed between -0.95 and 0.95). Use those values to compute the corresponding $\\alpha$ and $J^{bias}$ parameters for each neuron. The encoders $e$ are randomly chosen and are either +1 or -1 for each neuron. Go through the following steps:\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "