“Zhiyong Zhang”版本间的差异
来自cslt Wiki
（→Task schedule） |
|||
| （相同用户的13个中间修订版本未显示） | |||
| 第1行： | 第1行： | ||
| − | |||
| − | === | + | |
| + | =Papers To Read = | ||
| + | * 1, Learned-Norm pooling for deep feedforward and recurrent neural networks | ||
| + | |||
| + | |||
| + | =Task schedules= | ||
| + | |||
| + | ==Summary== | ||
-------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | ||
Priority | Tasks name | Status | Notions | Priority | Tasks name | Status | Notions | ||
-------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | ||
| − | 1 | Bi-Softmax | | + | 1 | Bi-Softmax | ■■■□□□□□□□ | 1400h am training and problem fixing |
-------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | ||
2 | RNN+DAE | □□□□□□□□□□ | | 2 | RNN+DAE | □□□□□□□□□□ | | ||
| 第15行： | 第21行： | ||
* Using two distinct softmax for English and Chinese data. | * Using two distinct softmax for English and Chinese data. | ||
* Testing on 100h-Ch+100h-En, better performance observed. | * Testing on 100h-Ch+100h-En, better performance observed. | ||
| − | * Now testing the source code on 1400h_8k data, but stange decoding results got. | + | * Now testing the source code on 1400h_8k data, but stange decoding results got.Need to further investigate. |
| − | + | ||
| − | + | ||
| − | + | ||
| − | == | + | =Reading Lists= |
| + | *[[媒体文件:Efficient_mini-batch_training_for_stochastic_optimization.pdf |苏圣 2015-10-29 Efficient_mini-batch_training_for_stochastic_optimization ]] | ||
| + | *[[媒体文件:2015_Fitnets-Hints for thin deep nets.pdf |张之勇 2015-10-29 2015_Fitnets-Hints for thin deep nets ]] | ||
| + | *http://www.cs.cmu.edu/~muli/file/minibatch_sgd.pdf | ||
2015年10月29日 (四) 07:14的最后版本
目录
Papers To Read
- 1, Learned-Norm pooling for deep feedforward and recurrent neural networks
Task schedules
Summary
--------------------------------------------------------------------------------------------------------
Priority | Tasks name | Status | Notions
--------------------------------------------------------------------------------------------------------
1 | Bi-Softmax | ■■■□□□□□□□ | 1400h am training and problem fixing
--------------------------------------------------------------------------------------------------------
2 | RNN+DAE | □□□□□□□□□□ |
--------------------------------------------------------------------------------------------------------
Speech Recognition
Multi-lingual Am training
Bi-Softmax
- Using two distinct softmax for English and Chinese data.
- Testing on 100h-Ch+100h-En, better performance observed.
- Now testing the source code on 1400h_8k data, but stange decoding results got.Need to further investigate.
