14-10-19 Dongxu Zhang - 版本历史

Zhangdx：/* Accomplished this week */

2014-10-20T00:41:27Z

‎Accomplished this week

2014-10-19T12:50:51Z

2014-10-19T12:46:48Z

‎Accomplished this week

2014-10-19T12:46:04Z

‎Accomplished this week

2014-10-19T12:45:47Z

‎Accomplished this week

2014-10-19T12:45:22Z

‎Accomplished this week

2014-10-19T12:44:44Z

‎Accomplished this week

2014-10-19T12:43:37Z

‎Next week

2014-10-19T12:43:24Z

‎Accomplished this week

2014-10-19T12:42:36Z

@@ 第1行： / 第1行： @@
 === 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 LSTM-Rnn LM with 200MB corpus(vocabulary 10k, classes 100, i100*m100). when using 2 cpu kernels, it takes aroung 200min per iteration.
 * Train 5-gram LM using Baiduzhidao_corpus(~30GB after preprocess) with new lexicon. There is a mistake when counted possiblity after merge.
 * Read paper "Learning Long-Term Dependencies with Gradient Descent is Difficult". Still in progress.

←上一版本		2014年10月19日 (日) 12:50的版本
第10行：		第10行：
	* Understand the paper.		* Understand the paper.
	* May have time to achieve my baseline idea on text8.		* May have time to achieve my baseline idea on text8.
		+
		+
		+	=== Myself ===
		+	* Prepare for toefl test.
		+	* prepare for master's thesis.

@@ 第3行： / 第3行： @@
 * Train 5-gram LM using Baiduzhidao_corpus(~30GB after preprocess) with new lexicon. There is a mistake when counted possiblity after merge.
 * Read paper "Learning Long-Term Dependencies with Gradient Descent is Difficult". Still in progress.
-* An idea occured to me which may improve the performance of word2vec with much more semantic information added. But there is huge computation complexity problem that bothers me, which I wish we can discuss.
+* An idea occured to me which may improve the performance of word2vec with much more semantic information added. But there is huge computation complexity problem that bothers me, which I wish we can discuss about.
 === Next week ===

@@ 第3行： / 第3行： @@
 * Train 5-gram LM using Baiduzhidao_corpus(~30GB after preprocess) with new lexicon. There is a mistake when counted possiblity after merge.
 * Read paper "Learning Long-Term Dependencies with Gradient Descent is Difficult". Still in progress.
-* An idea occured to me which may improve word2vec with much more semantic information added. But there is huge computation complexity problem that bothers me, which I wish we can discuss.
+* An idea occured to me which may improve the performance of word2vec with much more semantic information added. But there is huge computation complexity problem that bothers me, which I wish we can discuss.
 === Next week ===

@@ 第3行： / 第3行： @@
 * Train 5-gram LM using Baiduzhidao_corpus(~30GB after preprocess) with new lexicon. There is a mistake when counted possiblity after merge.
 * Read paper "Learning Long-Term Dependencies with Gradient Descent is Difficult". Still in progress.
-* 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 added. But there is huge computation complexity problem that bothers me, which I wish we can discuss.
 === Next week ===

@@ 第6行： / 第6行： @@
 === Next week ===
-* 1. Test LSTM-Rnn LM.
+* Test LSTM-Rnn LM.
-* 2. Finished building lexion.
+* Finished building lexion.
-* 3. Understand the paper.
+* Understand the paper.
-* 4. May have time to achieve my baseline idea on text8.
+* May have time to achieve my baseline idea on text8.