Hi, I was experimenting with LSTMs and noted that the dropout was applied at the output of the LSTMs like in the figure in the left below . I was wondering if it is possible to apply the dropout at the state transitions instead like on the right. [D]

h and c are not learned parameters. Check this example please: http://pytorch.org/tutorials/beginner/nlp/sequence_models_tutorial.html#example-an-lstm-for-part-of-speech-tagging

Dropout for LSTM state transitions

Irfan_Bulu (Irfan Bulu) May 1, 2018, 10:33pm 11

maybe the this discussion might help: