Zhiyuan Tang 2015-03-30

Last week:

preliminarily confirmed DNN's sparsity from the weights by Matlab and showed the weights' distribution graphicly;

more systematic knowlege about ASR has been gained;

CONTEXT was not yet studied carefully, :(

This week:

discover more things in the weights if it has more;

do some literature analysis about CONTEXT;

go through the OBD-based sparse DNN-HMM.