Zhiyuan Thang 15-06-29

Last few weeks (lazy):

Presently got the conclusion that randoming the weights ahead of softmax of DNN before MPE training may be not helpful.

Using language vector to pre-train the hidden layers of DNN gives at least a little improvement.

have not realized leaky Rectifier and temporal Rectifier, CUDA programing may be needed.

This week:

realize the two kinds of Rectifier.