“Zhiyuan Tang 2015-03-30”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
第13行: 第13行:
 
discover more things in the weights if it has more;
 
discover more things in the weights if it has more;
  
do some literture analysis about CONTEXT;
+
do some literature analysis about CONTEXT;
  
 
go through the OBD-based sparse DNN-HMM.
 
go through the OBD-based sparse DNN-HMM.

2015年3月30日 (一) 14:34的最后版本

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.