“Zhiyong Zhang”版本间的差异
来自cslt Wiki
| 第24行： | 第24行： | ||
=Reading Lists= | =Reading Lists= | ||
| − | *[[Efficient_mini-batch_training_for_stochastic_optimization |苏圣 2015-10-29 Efficient_mini-batch_training_for_stochastic_optimization | + | *[[媒体文件:Efficient_mini-batch_training_for_stochastic_optimization.pdf |苏圣 2015-10-29 Efficient_mini-batch_training_for_stochastic_optimization ]] |
*http://www.cs.cmu.edu/~muli/file/minibatch_sgd.pdf | *http://www.cs.cmu.edu/~muli/file/minibatch_sgd.pdf | ||
2015年10月29日 (四) 07:13的版本
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.
