“Mengyuan Zhao 2015-09-07”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“#reproduce batch-normalization experiment on aurora4 dataset. get similar result with ZZY #test Ad-grd and Ad-Max on sino 100h cn dataset. Ad-Max's result is not goo...”为内容创建页面)
 
(没有差异)

2015年9月7日 (一) 13:37的最后版本

  1. reproduce batch-normalization experiment on aurora4 dataset. get similar result with ZZY
  2. test Ad-grd and Ad-Max on sino 100h cn dataset. Ad-Max's result is not good. Ad-grd looks reasonable(tr_acc, cv_acc is ok), but training diverge after 5 iters.
  3. fix the bug of tag-lm while doing biglm decoding with multi tag.