Tianyi Luo 2016-05-02 - 版本历史

2016年5月9日 (一) 10:44 Lty

2016-05-09T10:44:08Z

2016年4月28日 (四) 09:13 Lty

2016-04-28T09:13:25Z

2016年4月28日 (四) 06:26 Lty

2016-04-28T06:26:44Z

2016年4月27日 (三) 18:52 Lty

2016-04-27T18:52:03Z

2016年4月27日 (三) 18:50 Lty

2016-04-27T18:50:58Z

2016年4月27日 (三) 18:49 Lty

2016-04-27T18:49:10Z

2016年4月27日 (三) 18:47 Lty

2016-04-27T18:47:33Z

Lty：以“=== Plan to do this week === * To implement tensorflow version of RNN/LSTM Max margin vector training. === Work done in this week === --------------------2016-04-26...”为内容创建页面

2016-04-27T18:46:49Z

以“=== Plan to do this week === * To implement tensorflow version of RNN/LSTM Max margin vector training. === Work done in this week === --------------------2016-04-26...”为内容创建页面

新页面

=== Plan to do this week ===
* To implement tensorflow version of RNN/LSTM Max margin vector training.
=== Work done in this week ===
--------------------2016-04-26

--------------------2016-04-27

--------------------2016-04-28

--------------------2016-04-29

--------------------2016-04-30

--------------------2016-05-01

--------------------2016-05-02

=== Plan to do next week ===
* To implement tensorflow version of RNN/LSTM Max margin vector training.
* To implement attention chatting model with xiaobing corpus.
===Interested papers ===
*Cascading Bandits: Learning to Rank in the Cascade Model(ICML 2015) [[http://zheng-wen.com/Cascading_Bandit_Paper.pdf pdf]]

@@ 第4行： / 第4行： @@
 === Work done in this week ===
 --------------------2016-04-25
-* Conduct some preprocess of xiaobing corpus.
+* Conduct some preprocessing of xiaobing corpus.
 --------------------2016-04-26
 * Help jiyuan to understand the music generation paper.
@@ 第11行： / 第11行： @@
 * Modify the LSTM Max margin vector training code. Its cost is lower than RNN and the training speed is slower than RNN. The performance improves from 82.39% to 84.83%.
 --------------------2016-04-28
+* Finish part of code about qaa(Current sample is q1; Positive sample is a1; Negtive sampling is a2.) max margin theano version.
 --------------------2016-04-29
+* Finish the code about qaa(Current sample is q1; Positive sample is a1; Negtive sampling is a2.) max margin theano version.
---------------------2016-04-30
+--------------------2016-04-30~2016-05-01
+The Holiday of Labors Day
---------------------2016-05-01

@@ 第9行： / 第9行： @@
 * Check jiyuan's code(from RNN-RBM to LSTM-RBM).
 --------------------2016-04-27
-* Modify the LSTM Max margin vector training. Its cost is lower than RNN and the training speed is slower than RNN. The performance improve from 82.39% to 84.83%.
+* Modify the LSTM Max margin vector training code. Its cost is lower than RNN and the training speed is slower than RNN. The performance improves from 82.39% to 84.83%.
 --------------------2016-04-28

@@ 第9行： / 第9行： @@
 * Check jiyuan's code(from RNN-RBM to LSTM-RBM).
 --------------------2016-04-27
-* Modify the LSTM Max margin vector training. Its cost is lower than RNN and the training speed is slower than RNN.
+* Modify the LSTM Max margin vector training. Its cost is lower than RNN and the training speed is slower than RNN. The performance improve from 82.39% to 84.83%.
 --------------------2016-04-28

@@ 第4行： / 第4行： @@
 === Work done in this week ===
 --------------------2016-04-25
 --------------------2016-04-26
 * Help jiyuan to understand the music generation paper.

@@ 第4行： / 第4行： @@
 === Work done in this week ===
 --------------------2016-04-25
 --------------------2016-04-26
+* Help jiyuan to understand the music generation paper.
 --------------------2016-04-27
-* Implement LSTM Max margin vector training. Its cost is lower than RNN and the training speed is slower than RNN.
+* Modify the LSTM Max margin vector training. Its cost is lower than RNN and the training speed is slower than RNN.
 --------------------2016-04-28

@@ 第1行： / 第1行： @@
 === Plan to do this week ===
 * To implement tensorflow version of RNN/LSTM Max margin vector training.
 === Work done in this week ===
 --------------------2016-04-26
@@ 第13行： / 第16行： @@
 --------------------2016-05-01