theanets

theanets copied to clipboard

Hidden_l1 problem

1

If I don't specify a certain layer for the hidden_l1 restriction with dict() it won't apply the regularization (therefore error = loss all the time). Are there any news on...

jamona

Recurrent models should accept nonzero initial state

1

To sample sequentially from a recurrent model, it would be useful to add some API for accepting an initial hidden state and running the model forward one time step.

lmjohns3

add "bayesian rnn" implementation

1

http://arxiv.org/pdf/1512.05287v1.pdf Yarin Gal has a paper describing an LSTM that uses a "fixed" dropout mask to remove LSTM cells. It would be cool to have an implementation of this in...

lmjohns3

We should try to make sure theanets doesn't leak!

lmjohns3

Goal: Predict multivariate time-series with exogenous variables Assuming a pandas DataFrame with T rows and M+N columns, where each row t represents one time stamp, M columns represent the corresponding...

kzk2000

Layerwise GPU memory use

1

Hi, I have a feeling that layerwise optimizer, by creating numerous networks is not freeing past networks and using more GPU memory than it should. I'm having a heck of...

abramhindle