Mengyuan Zhao 2016-02-22

来自cslt Wiki
跳转至： 导航、 搜索
  1. 7*2048 chain model trainning done, worse than nnet3 model.
  2. Study nnet3 LSTM configuration in detail, and try to run chain training with modified LSTM structure.
取自“http://index.cslt.org/mediawiki/index.php?title=Mengyuan_Zhao_2016-02-22&oldid=19085”