“14-10-19 Dongxu Zhang”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
Next week
Accomplished this week
第1行: 第1行:
 
=== Accomplished this week ===
 
=== Accomplished this week ===
* Train LSTM-Rnn LM with 200MB corpus(vocabulary 10k, classes 100). when using 2 kernels, it takes aroung 200min per epoch.
+
* Train LSTM-Rnn LM with 200MB corpus(vocabulary 10k, classes 100, i100*m100). when using 2 cpu kernels, it takes aroung 200min per epoch.  
 
* Train 5-gram LM using Baiduzhidao_corpus(~30GB after preprocess) with new lexicon. There is a mistake when counted possiblity after merge.
 
* Train 5-gram LM using Baiduzhidao_corpus(~30GB after preprocess) with new lexicon. There is a mistake when counted possiblity after merge.
 
* An idea occured to me which may improve word2vec with much more semantic information. But there is huge computation complexity problem that bothers me, which I wish we can discuss.
 
* An idea occured to me which may improve word2vec with much more semantic information. But there is huge computation complexity problem that bothers me, which I wish we can discuss.

2014年10月19日 (日) 12:44的版本

Accomplished this week

  • Train LSTM-Rnn LM with 200MB corpus(vocabulary 10k, classes 100, i100*m100). when using 2 cpu kernels, it takes aroung 200min per epoch.
  • Train 5-gram LM using Baiduzhidao_corpus(~30GB after preprocess) with new lexicon. There is a mistake when counted possiblity after merge.
  • An idea occured to me which may improve word2vec with much more semantic information. But there is huge computation complexity problem that bothers me, which I wish we can discuss.
  • Read paper "Learning Long-Term Dependencies with Gradient Descent is Difficult". Still in progress.

Next week

  • Test LSTM-Rnn LM.
  • Finished building lexion.
  • Understand the paper.
  • May have time to achieve my baseline idea on text8.