Closed chqiwang closed 8 years ago
Hi! @glample ,why LSTM's forget gate are not used? Will the forget gate hurt the performance? Any explanation on that?
Hello, This small modification reduces the number of parameters, and makes the training a little bit faster. However, I didn't observe significant differences of scores with and without it.
Hi! @glample ,why LSTM's forget gate are not used? Will the forget gate hurt the performance? Any explanation on that?