GroundHog
GroundHog copied to clipboard
Library for implementing RNNs with Theano
Results
2
GroundHog issues
Sort by
recently updated
recently updated
newest added
You
2
> Fixes #
Dear all, to my knowledge it's at the moment not possible to train the initial state of a recurrent layer (rec_layer.py). For same applications this is helpfull and quite common....