“Mengyuan Zhao 2015-09-21”版本间的差异

2015年9月21日 (一) 04:06的最后版本

Track LSTM MPE training on Ping"AnBaoxian 700h & 1400h+100h cn-en & 1700h+776h cn dataset.
Do a series of experiments about gradient optimization algorithm on sinovoice & tencent dataset. Got some results but still worse than SGD baseline.

2015年9月21日 (一) 04:05的版本（查看源代码） Zhaomy（讨论 \| 贡献）（以“#Track LSTM MPE training on Ping"AnBaoxian 700h & 1400h+100h cn-en dataset. #Do a series of experiments about gradient optimization algorithm on sinovoice & tencent...”为内容创建页面）		2015年9月21日 (一) 04:06的最后版本（查看源代码） Zhaomy（讨论 \| 贡献）
第1行：		第1行：
−	#Track LSTM MPE training on Ping"AnBaoxian 700h & 1400h+100h cn-en dataset.	+	#Track LSTM MPE training on Ping"AnBaoxian 700h & 1400h+100h cn-en & 1700h+776h cn dataset.
	#Do a series of experiments about gradient optimization algorithm on sinovoice & tencent dataset. Got some results but still worse than SGD baseline.		#Do a series of experiments about gradient optimization algorithm on sinovoice & tencent dataset. Got some results but still worse than SGD baseline.