Yan Yin

Hi All, I want to setup using global learning rate instead of learning rate matrix,...

Hi All, Can anyone share your experience about below online natural gradient configuration...

an extreme case is, If I want to build a shrinking network (hidden layer size keep...

I guess what I can do is, initiliaze network with input, low rank, and output layers,...

I guess what I can do is, initiliaze network with input, low rank, and output layers,...

Hi All, As I see from existing Kaldi recipe, we usually start with network with one...

Hi All, As I see from existing Kaldi recipe, we usually start with network with one...