Regularization
Variational Dropout
Introduced by Gal et al. in A Theoretically Grounded Application of Dropout in Recurrent Neural NetworksVariational Dropout is a regularization technique based on dropout, but uses a variational inference grounded approach. In Variational Dropout, we repeat the same dropout mask at each time step for both inputs, outputs, and recurrent layers (drop the same network units at each time step). This is in contrast to ordinary Dropout where different dropout masks are sampled at each time step for the inputs and outputs alone.
Source: A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 61 | 24.11% |
| Text Classification | 15 | 5.93% |
| General Classification | 15 | 5.93% |
| Sentiment Analysis | 12 | 4.74% |
| Classification | 8 | 3.16% |
| Translation | 8 | 3.16% |
| Machine Translation | 8 | 3.16% |
| Speech Recognition | 7 | 2.77% |
| Sentence | 6 | 2.37% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
