Merge pull request lisa-lab#67 from carriepl/sgd_in_lstm_tutorial

nouiz · nouiz · commit b28a15284dc8 · 2015-01-13T13:25:11.000-05:00
Add notice about using SGD in the LSTM tutorial
diff --git a/doc/lstm.txt b/doc/lstm.txt
@@ -194,6 +194,11 @@ can run the code by calling:
 
 The script will automatically download the data and decompress it.
 
+**Note** : The provided code supports the Stochastic Gradient Descent (SGD),
+AdaDelta and RMSProp optimization methods. You are advised to use AdaDelta or
+RMSProp because SGD appears to performs poorly on this task with this
+particular model.
+
 Papers
 ======
 
