Building a Neural Network

Author: TarrySingh

deep-learning/Generelizing Mutiple Layers.ipynb

@@ -0,0 +1,44 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Vectorization\n",
+    "\n",
+    "This part will cover:\n",
+    "\n",
+    "- Vectorization of backpropagation\n",
+    "- Gradient checking\n",
+    "- Momentum\n",
+    "\n",
+    "The previous tutorial described a very simple neural network with only one input, one hidden neuron and one output. This tutorial will describe a neural network that takes 2-dimensional input samples, projects them onto a 3-dimensional hidden layer, and classifies them with a 2-dimensional softmax output classfier, this softmax function is explained in Logistic/Softmax Notebook. \n",
+    "\n",
+    "While we didn't add the bias parameters to the previous 2 models, we will add them to this model. We will work out the vector computations needed to optimize and run this neural network in this tutorial. The network of this model is shown in the following figure:\n",
+    "\n",
+    "Image of the neural network"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}