Gilles Louppe

Peter, are you aware of PyLearn? http://deeplearning.net/software/pylearn2/features.html#features They have a lot of stuff for DBNs. It might be interesting to look at the preprocessing modules they have.

Peter, what is your current best parameters? The ones above with epochs_pretrain=10? Do you want me to grid-search the parameters? with or without all mfcc?

Adding activations lead to (significantly) poorer results... ``` ['2200', 'gbrt', '2500', '8', '0.125', '0.01', '26', '1.0'] Loading data... importances.shape = (14270,) X.shape = (30000, 14270) X_train.shape = (15000, 2450) y_train.shape...

Here is the mean spectrogram for the instances for which GBRT predicts a proba p such that: p < 0.01  0.01

Whoah! I love it. That's indeed a lot more useful than all I tried to do until now :) The false positives are really stunning. I really wonder what the...