readme update

Author: IanBurke1

Architecture.ipynb

@@ -0,0 +1,91 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Artificial Neural Network"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Artificial Neural Network (ANN) is a computational model that is inspired by the way biological neural networks in the human brain process information. Artificial Neural Networks have generated a lot of excitement in Machine Learning research and industry. The basic unit of computation in a neural network is the neuron, often called a node or unit. It receives input from some other nodes, or from an external source and computes an output. Each input has an associated weight (w), which is assigned on the basis of its relative importance to other inputs.\n",
+    "\n",
+    "![](https://ujwlkarn.files.wordpress.com/2016/08/screen-shot-2016-08-09-at-3-42-21-am.png?w=768&h=410)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Convolutional Neural Network"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Convolutional Neural Networks (CNN) are multi-layer neural networks that have successfully been applied to analyzing visual imagery. The main feature of CNN's is that it can drastically reduce the number of parameters that need to be tuned. This means that CNN's can efficiently handle the high dimensionality of raw images. \n",
+    "\n",
+    "![](https://www.pyimagesearch.com/wp-content/uploads/2014/06/cnn_architecture.jpg)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# MNIST Data Set"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "MNIST is a famous dataset that consists of handwritten digits commonly used for training various image processing systems and also used in machine learning. The dataset contains 60,000 training images and 10,000 testing images. Each image is a 28x28 pixel square (784 pixels in total). A standard split of the dataset is used to evaluate and compare models. Excellent results achieve a prediction error/loss of less than 1% and accuracy of up to 0.99%.\n",
+    "#### References:\n",
+    "- The MNIST Database - http://yann.lecun.com/exdb/mnist/\n",
+    "- https://machinelearningmastery.com/handwritten-digit-recognition-using-convolutional-neural-networks-python-keras/\n",
+    "\n",
+    "![](https://www.tensorflow.org/images/mnist_digits.png)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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
+}