@fchollet i haven't had much luck with anything besides clipped RMSProp with momentum. Adam, adadelta, etc never seem to quite get it.
There's also the fact that gradient decent gets really weird when it comes to RNNs
-
-
-
@kastnerkyle At least in this example, replacing rmsprop with adam (default params) resulted in x2 convg. speed : ) https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py … - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.