Mengyuan Zhao 2015-09-08

来自cslt Wiki
跳转至： 导航、 搜索
  1. reproduce batch-normalization experiments on aurora4 dataset. got similar results as ZZY.
  2. test Ad-grd & Ad-max on sino-100h dataset. Ad-max is bad. Ad-grd looks reasonable, but training diverge after 5 iters.
取自“http://index.cslt.org/mediawiki/index.php?title=Mengyuan_Zhao_2015-09-08&oldid=16650”