Merge pull request #141 from cvanderw/char-rnn-typos

Fix minor typos in char rnn notebooks

Author: jchernus

recurrent-neural-networks/char-rnn/Character_Level_RNN_Exercise.ipynb

@@ -324,7 +324,7 @@
     "In `__init__` the suggested structure is as follows:\n",
     "* Create and store the necessary dictionaries (this has been done for you)\n",
     "* Define an LSTM layer that takes as params: an input size (the number of characters), a hidden layer size `n_hidden`, a number of layers `n_layers`, a dropout probability `drop_prob`, and a batch_first boolean (True, since we are batching)\n",
-    "* Define a dropout layer with `dropout_prob`\n",
+    "* Define a dropout layer with `drop_prob`\n",
     "* Define a fully-connected layer with params: input size `n_hidden` and output size (the number of characters)\n",
     "* Finally, initialize the weights (again, this has been given)\n",
     "\n",
@@ -557,7 +557,7 @@
    },
    "outputs": [],
    "source": [
-    "## TODO: set you model hyperparameters\n",
+    "## TODO: set your model hyperparameters\n",
     "# define and print the net\n",
     "n_hidden=\n",
     "n_layers=\n",

recurrent-neural-networks/char-rnn/Character_Level_RNN_Solution.ipynb

@@ -383,7 +383,7 @@
     "In `__init__` the suggested structure is as follows:\n",
     "* Create and store the necessary dictionaries (this has been done for you)\n",
     "* Define an LSTM layer that takes as params: an input size (the number of characters), a hidden layer size `n_hidden`, a number of layers `n_layers`, a dropout probability `drop_prob`, and a batch_first boolean (True, since we are batching)\n",
-    "* Define a dropout layer with `dropout_prob`\n",
+    "* Define a dropout layer with `drop_prob`\n",
     "* Define a fully-connected layer with params: input size `n_hidden` and output size (the number of characters)\n",
     "* Finally, initialize the weights (again, this has been given)\n",
     "\n",