-
由 Razvan Pascanu 提交于
The bug is that we do not clip the sequences to n_steps, meaning that when we revert them for computing the gradient we mess up the gradient.
80f150b2
The bug is that we do not clip the sequences to n_steps, meaning that when we revert them for computing the gradient we mess up the gradient.
| 名称 |
最后提交
|
最后更新 |
|---|---|---|
| benchmark | 正在载入提交数据... | |
| bin | 正在载入提交数据... | |
| doc | 正在载入提交数据... | |
| theano | 正在载入提交数据... | |
| .gitignore | 正在载入提交数据... | |
| DESCRIPTION.txt | 正在载入提交数据... | |
| EMAIL.txt | 正在载入提交数据... | |
| HISTORY.txt | 正在载入提交数据... | |
| LICENSE.txt | 正在载入提交数据... | |
| MANIFEST.in | 正在载入提交数据... | |
| NEWS.txt | 正在载入提交数据... | |
| README.txt | 正在载入提交数据... | |
| distribute_setup.py | 正在载入提交数据... | |
| setup.cfg | 正在载入提交数据... | |
| setup.py | 正在载入提交数据... |