“Tianyi Luo 2016-05-02”版本间的差异

2016年4月27日 (三) 18:50的版本 （查看源代码） Lty（讨论 | 贡献） ←上一编辑		2016年4月27日 (三) 18:52的版本 （查看源代码） Lty（讨论 | 贡献） 下一编辑→
第4行：		第4行：
	=== Work done in this week ===		=== Work done in this week ===
	--------------------2016-04-25		--------------------2016-04-25
		+	* Conduct some preprocess of xiaobing corpus.
	--------------------2016-04-26		--------------------2016-04-26
	* Help jiyuan to understand the music generation paper.		* Help jiyuan to understand the music generation paper.

---

2016年4月27日 (三) 18:52的版本

Plan to do this week

• To implement tensorflow version of RNN/LSTM Max margin vector training.
• To implement attention chatting model with xiaobing corpus.

Work done in this week

---

2016-04-25

• Conduct some preprocess of xiaobing corpus.

---

2016-04-26

• Help jiyuan to understand the music generation paper.
• 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.

---

2016-04-28

---

2016-04-29

---

2016-04-30

---

2016-05-01

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) [pdf]