Dropout with Expectation-linear Regularization
Open
enhancement
- Dominant language
- C++
- Stars
- 3.4k
- Forks
- 701
- PR merge metrics
- No merged PRs in 30d
Description
[Ma et al. (2017)](https://arxiv.org/abs/1609.08017) introduce dropout with regularization (DR), the benefit of which in NLP is shown by [Strubell et al. (2017)](https://arxiv.org/abs/1702.02098). Does DyNet dropout support this regularization?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.