{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Nengo Tutorial\n",
    "\n",
    "## Nengo\n",
    "\n",
    "- Our neural simulator\n",
    "- Implements the basics of what we cover in this class\n",
    "    - So you don't have to worry about the implementation details\n",
    "    - But understanding the theory will help you use it better\n",
    "    \n",
    "- website: [Nengo.ca](http://nengo.ca)\n",
    "- install: [Download Nengo](http://nengo.ca/download)\n",
    "    - use the \"latest development version of Nengo\"\n",
    "    - Java application; runs on Linux, OS X, Windows\n",
    "    - Open Source: [Github repository](https://github.com/ctn-waterloo/nengo_1.4)\n",
    "\n",
    "## How to use it\n",
    "\n",
    "- Drag and drop interface: [Tutorials](http://nengo.ca/docs/html/tutorial.html)\n",
    "- Python scripting: [Tutorials](http://nengo.ca/docs/html/scripting.html)\n",
    "- basic usage:\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import nef\n",
    "net = nef.Network('Example')\n",
    "net.make_input('input', [0])\n",
    "\n",
    "net.make('A', neurons=75, dimensions=1)\n",
    "net.make('B', neurons=50, dimensions=1)\n",
    "\n",
    "def square(x):\n",
    "    return x[0]*x[0]\n",
    "\n",
    "net.connect('A', 'B', func=square)\n",
    "\n",
    "net.connect('input', 'A')\n",
    "\n",
    "net.add_to_nengo()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- More advanced usage\n",
    "    - the ``make`` command builds ensembles\n",
    "         - [documentation](http://nengo.ca/docs/html/nef.Network.html#nef.Network.make)\n",
    "    - the ``connect`` command forms connections between ensembles\n",
    "         - [documentation](http://nengo.ca/docs/html/nef.Network.html#nef.Network.connect)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The creature we made in class\n",
    "\n",
    "- Should set ``motor`` to be the direction we tell it to go in with ``command``, unless ``scared`` is 1, in which can it should try to go back to ``position`` (0,0)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import nef\n",
    "\n",
    "net = nef.Network('Creature')\n",
    "\n",
    "net.make_input('command_input', [0,0])\n",
    "\n",
    "net.make('command', neurons=100, dimensions=2)\n",
    "\n",
    "net.make('motor', neurons=100, dimensions=2)\n",
    "\n",
    "net.make('position', neurons=1000, dimensions=2, radius=5)\n",
    "\n",
    "net.make('scared_direction', neurons=100, dimensions=2)\n",
    "\n",
    "def negative(x):\n",
    "    return -x[0], -x[1]\n",
    "\n",
    "net.connect('position', 'scared_direction', func=negative)\n",
    "\n",
    "net.connect('position', 'position')\n",
    "\n",
    "net.make('plan', neurons=500, dimensions=5)\n",
    "net.connect('command', 'plan', index_post=[0,1])\n",
    "net.connect('scared_direction', 'plan', index_post=[2,3])\n",
    "net.make('scared', neurons=50, dimensions=1)\n",
    "net.make_input('scared_input', [0])\n",
    "net.connect('scared_input', 'scared')\n",
    "net.connect('scared', 'plan', index_post=[4])\n",
    "\n",
    "def plan_function(x):\n",
    "    c_x, c_y, s_x, s_y, s = x\n",
    "    return s*(s_x)+(1-s)*c_x, s*(s_y)+(1-s)*c_y\n",
    "    \n",
    "net.connect('plan', 'motor', func=plan_function)    \n",
    "\n",
    "\n",
    "def rescale(x):\n",
    "    return x[0]*0.1, x[1]*0.1\n",
    "\n",
    "net.connect('motor', 'position', func=rescale)\n",
    "\n",
    "\n",
    "net.connect('command_input', 'command')\n",
    "\n",
    "net.add_to_nengo()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}