MNIST

Author: atcemgil

BayesianLinearModel.ipynb

@@ -0,0 +1,53 @@
+#Code from https://gist.github.com/craffel/2d727968c3aaebd10359
+
+import matplotlib.pyplot as plt
+
+def draw_neural_net(ax, left, right, bottom, top, layer_sizes, bias=0, draw_edges=False):
+    '''
+    Draw a neural network cartoon using matplotilb.
+    
+    :usage:
+        >>> fig = plt.figure(figsize=(12, 12))
+        >>> draw_neural_net(fig.gca(), .1, .9, .1, .9, [4, 7, 2])
+    
+    :parameters:
+        - ax : matplotlib.axes.AxesSubplot
+            The axes on which to plot the cartoon (get e.g. by plt.gca())
+        - left : float
+            The center of the leftmost node(s) will be placed here
+        - right : float
+            The center of the rightmost node(s) will be placed here
+        - bottom : float
+            The center of the bottommost node(s) will be placed here
+        - top : float
+            The center of the topmost node(s) will be placed here
+        - layer_sizes : list of int
+            List of layer sizes, including input and output dimensionality
+        - bias : Boolean
+            Draw an extra bias node at each layer
+        - draw_edges : Boolean
+            If false, omit edge connections
+    '''
+    n_layers = len(layer_sizes)
+    v_spacing = (top - bottom)/float(max(layer_sizes)+bias)
+    h_spacing = (right - left)/float(len(layer_sizes) - 1)
+    # Nodes
+    for n, layer_size in enumerate(layer_sizes):
+        layer_top = v_spacing*(layer_size - 1)/2. + (top + bottom)/2.
+        bias_node = (bias if n<len(layer_sizes)-1 else 0)
+        for m in range(layer_size+bias_node ):
+            node_color = 'w' if m<layer_size else 'b'
+            circle = plt.Circle((n*h_spacing + left, layer_top - m*v_spacing), v_spacing/8.,
+                                color=node_color, ec='k', zorder=4)
+            ax.add_artist(circle)
+    # Edges
+    if draw_edges:
+        for n, (layer_size_a, layer_size_b) in enumerate(zip(layer_sizes[:-1], layer_sizes[1:])):
+            layer_top_a = v_spacing*(layer_size_a - 1)/2. + (top + bottom)/2.
+            layer_top_b = v_spacing*(layer_size_b - 1)/2. + (top + bottom)/2.
+            for m in range(layer_size_a+bias):
+                for o in range(layer_size_b):
+                    line = plt.Line2D([n*h_spacing + left, (n + 1)*h_spacing + left],
+                                      [layer_top_a - m*v_spacing, layer_top_b - o*v_spacing], 
+                                      c='k')
+                    ax.add_artist(line)

DrawNN.py

@@ -2,10 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "# The Kalman Filter\n",
     "\n",
@@ -14,10 +11,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## The Linear Dynamical System (LDS)\n",
     "\n",
@@ -71,10 +65,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "Example: A point object moving with (almost) constant velocity.\n",
     "\n",
@@ -84,10 +75,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "The input to the algorithm are the parameters and a sequence of \n",
     "observations $y_t$ for $t=1 \\dots T$\n",
@@ -150,9 +138,6 @@
    "cell_type": "code",
    "execution_count": 24,
    "metadata": {
-    "collapsed": false,
-    "deletable": true,
-    "editable": true,
     "scrolled": false
    },
    "outputs": [
@@ -218,10 +203,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "## Your Task:\n",
     "\n",
@@ -260,10 +242,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "The new algorithm is as follows\n",
     "## Kalman Filter with incremental updates\n",
@@ -339,11 +318,7 @@
   {
    "cell_type": "code",
    "execution_count": 18,
-   "metadata": {
-    "collapsed": false,
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "A = np.mat('[1, 1; 0, 1]')\n",
@@ -363,10 +338,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "Below is a not very efficient and numerically unstable but nevertheless a readable implementation of the Kalman filter for your reference. For or small model sizes $M, N, T$ the results would give a base to test against. Cross check with your implementation that your numerical results are about the same.\n",
     "\n"
@@ -375,11 +347,7 @@
   {
    "cell_type": "code",
    "execution_count": 25,
-   "metadata": {
-    "collapsed": false,
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -443,10 +411,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
     "For $i=1 \\dots M$ (InnerFor)\n",
     "$$\n",
@@ -473,11 +438,7 @@
   {
    "cell_type": "code",
    "execution_count": 26,
-   "metadata": {
-    "collapsed": false,
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -549,9 +510,6 @@
    "cell_type": "code",
    "execution_count": 7,
    "metadata": {
-    "collapsed": false,
-    "deletable": true,
-    "editable": true,
     "scrolled": true
    },
    "outputs": [
@@ -589,9 +547,6 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {
-    "collapsed": false,
-    "deletable": true,
-    "editable": true,
     "scrolled": true
    },
    "outputs": [
@@ -651,11 +606,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": false,
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -707,7 +658,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python [default]",
    "language": "python",
    "name": "python3"
   },
@@ -721,9 +672,19 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.5"
+  },
+  "toc": {
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": "block",
+   "toc_window_display": false
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 1
 }