From 10efd26ec19dcaea8984cc5376a277c1cff09ac8 Mon Sep 17 00:00:00 2001
From: shaheeng <gauher@gmail.com>
Date: Mon, 24 Jul 2017 21:15:58 +0000
Subject: [PATCH] ipynb

---
 Train a Neural Network to Play Hangman.ipynb | 68 ++++++++------------
 1 file changed, 28 insertions(+), 40 deletions(-)

diff --git a/Train a Neural Network to Play Hangman.ipynb b/Train a Neural Network to Play Hangman.ipynb
index e501d9a..b9bbe03 100644
--- a/Train a Neural Network to Play Hangman.ipynb	
+++ b/Train a Neural Network to Play Hangman.ipynb	
@@ -36,31 +36,32 @@
     "<a name=\"setup\"></a>\n",
     "## Set up the execution environment\n",
     "\n",
-    "We created a GPU VM with CNTK 2.0 RC2 pre-installed using the [Azure Deep Learning toolkit for the DSVM](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/microsoft-ads.dsvm-deep-learning) and set up the VM's Jupyter Notebook server using the [provided instructions](https://docs.microsoft.com/en-us/azure/machine-learning/machine-learning-data-science-provision-vm#how-to-create-a-strong-password-for-jupyter-and-start-the-notebook-server). We then loaded this notebook on the VM before executing the code cells below.\n",
+    "There are two readily available options on Azure to run this notebook if you should choose to do so.\n",
     "\n",
-    "VM images are updated regularly, but at the time of this writing, the following package versions were pre-installed in the `py35` Anaconda environment on the VM:"
+    "1) Create a GPU VM with CNTK 2.0 RC2 pre-installed using the [Azure Deep Learning toolkit for the DSVM](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/microsoft-ads.dsvm-deep-learning) and set up the VM's Jupyter Notebook server using the [provided instructions](https://docs.microsoft.com/en-us/azure/machine-learning/machine-learning-data-science-provision-vm#how-to-create-a-strong-password-for-jupyter-and-start-the-notebook-server).\n",
+    "\n",
+    "2) Provision a [Microsoft Azure Data Science Virtual Machine (DSVM)](https://blogs.technet.microsoft.com/machinelearning/2017/06/06/introducing-the-new-data-science-virtual-machine-on-windows-server-2016/) with Windows Server 2016. They come  pre-installed with the GPU Nvidia drivers, CUDA toolkit 8.0, and cuDNN library.\n",
+    "\n",
+    "We then loaded this notebook on the VM before executing the code cells below. VM images are updated regularly, but at the time of this writing, the following package versions were pre-installed in the `py35` Anaconda environment on the VMs respectively:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The notebook was tested with   \n",
+    "Python version: 3.5.2 and 3.5.3  \n",
+    "Anaconda 4.4.0 (64-bit)  \n",
+    "CNTK version: 2.0rc2 and 2.0  \n",
+    "NumPy version: 1.11.2 and 1.13.0  \n",
+    "Pandas version: 0.19.1 and 0.20.0  "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Python version: 3.5.2 |Anaconda custom (64-bit)| (default, Jul  5 2016, 11:41:13) [MSC v.1900 64 bit (AMD64)]\n",
-      "CNTK version: 2.0rc2\n",
-      "NumPy version: 1.11.2\n",
-      "Pandas version: 0.19.1\n",
-      "\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import sys, cntk\n",
     "import numpy as np\n",
@@ -107,9 +108,7 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "word_dict = {}\n",
@@ -150,9 +149,7 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -383,7 +380,6 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "collapsed": false,
     "scrolled": true
    },
    "outputs": [],
@@ -449,9 +445,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -530,9 +524,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -564,9 +556,7 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -603,9 +593,7 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -639,7 +627,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.5.3"
   }
  },
  "nbformat": 4,