Add attribution

hatt_train.ipynb

@@ -2,14 +2,9 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "metadata": {
-    "deletable": true,
-    "editable": true
-   },
+   "metadata": {},
    "source": [
-    "First check the following dependencies: \n",
-    "\n",
-    "conda install theano pygpu"
+    "The code in this notebook is based on [Richard Liao's implementation of hierarchical attention networks](https://github.com/richliao/textClassifier/blob/master/textClassifierHATT.py) and a related [Google group discussion](https://groups.google.com/forum/#!topic/keras-users/IWK9opMFavQ). The notebook also includes code from [Keras documentation](https://keras.io/) and [blog](https://blog.keras.io/using-pre-trained-word-embeddings-in-a-keras-model.html) as well as this [word2vec tutorial](http://adventuresinmachinelearning.com/gensim-word2vec-tutorial/)."
    ]
   },
   {
@@ -19,17 +14,21 @@
     "editable": true
    },
    "source": [
-    "Replace $HOME/.theanorc with this:\n",
+    "To enable Theano to run on a single GPU: \n",
     "\n",
-    "[global]\n",
+    "* check the following dependencies: \n",
     "\n",
-    "floatX = float32\n",
+    "  `conda install pygpu`\n",
+    "  \n",
     "\n",
+    "* Replace $HOME/.theanorc with this:\n",
+    "```\n",
+    "[global]\n",
+    "floatX = float32\n",
     "device = gpu0\n",
-    "\n",
     "[lib]\n",
-    "\n",
-    "gpuarray.preallocate=1\n"
+    "gpuarray.preallocate=1\n",
+    "```"
    ]
   },
   {