Add files via upload

matrix-multiplication.ipynb

@@ -0,0 +1,223 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Matrix Multiplication"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Abstract"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Computation in TensorFlow is represented as a graph. \n",
+    "\n",
+    "Nodes in the graph are called ops (short for operations). An op takes zero or more Tensors (typed multi-dimensional arrays), performs some computation, and produces zero or more Tensors.\n",
+    "\n",
+    "A TensorFlow graph is a description of computations. To compute anything, a graph must be launched in a Session. A Session places the graph ops onto Devices, such as CPUs or GPUs, and provides methods to execute them."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Introduction"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This tutorial is taken, with slight modification and different annotations, from [TensorFlow's official documentation](https://www.tensorflow.org/versions/r0.11/get_started/basic_usage.html).\n",
+    "\n",
+    "This tutorial is intended for readers who are new to both machine learning and TensorFlow. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Graph Construction"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "First of all, we import the TensorFlow library."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import tensorflow as tf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We then create a _constant_ op that produces a 1x2 matrix.  The op is added as a node to the default graph.\n",
+    "\n",
+    "The value returned by the constructor represents the output of the Constant op."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "matrix1 = tf.constant([[3., 3.]])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We create another _constant_ that produces a 2x1 matrix."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "matrix2 = tf.constant([[2.],[2.]])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Finally, we create a _matmul_ op that takes _matrix1_ and _matrix2_ as inputs. The returned value, _product_, represents the result of the matrix multiplication."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "product = tf.matmul(matrix1, matrix2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Launching of the Session"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To compute anything, a graph must first be launched in a _Session_. Let's create our _Session_ by launching the default graph."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "sess = tf.Session()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To run the matmul op we call the session _run()_ method, passing _product_ (which represents the output of the matmul op). This indicates to the call that we want to get the output of the matmul op back.\n",
+    "\n",
+    "All inputs needed by the op are run automatically by the session. They typically are run in parallel.\n",
+    "\n",
+    "The call _run(product)_ thus causes the execution of three ops in the graph: the two constants and matmul.\n",
+    "\n",
+    "The output of the op is returned in _result_ as a numpy _ndarray_ object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[ 12.]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = sess.run(product)\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Once we are done, let's close the Session."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "sess.close()"
+   ]
+  }
+ ],
+ "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": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}