“Zhiyuan Thang 15-06-29”版本间的差异
来自cslt Wiki
| 第1行： | 第1行： | ||
Last few weeks (lazy): | Last few weeks (lazy): | ||
| + | |||
| + | training LSTM with MPE (failed); | ||
presently got the conclusion that randoming the weights ahead of softmax of DNN before MPE training may be not helpful; | presently got the conclusion that randoming the weights ahead of softmax of DNN before MPE training may be not helpful; | ||
2015年6月30日 (二) 14:46的版本
Last few weeks (lazy):
training LSTM with MPE (failed);
presently got the conclusion that randoming the weights ahead of softmax of DNN before MPE training may be not helpful;
using language vector to pre-train the hidden layers of DNN gives at least a little improvement, especially 3 hidden layers is pre-trained when DNN is of 4 hidden layers;
have not realized leaky Rectifier and temporal Rectifier, as CUDA programing may be needed;
paper reading.
This week:
realize the two kinds of Rectifier;
paper reading.
