Zoneout is a method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ensemble, improving generalization. But by preserving instead of dropping hidden units, gradient information and state information are more readily propagated through time, as in feedforward stochastic depth networks.
Source: Zoneout: Regularizing RNNs by Randomly Preserving Hidden ActivationsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Speech Synthesis | 14 | 34.15% |
Text-To-Speech Synthesis | 4 | 9.76% |
Language Modelling | 3 | 7.32% |
Voice Cloning | 2 | 4.88% |
Style Transfer | 2 | 4.88% |
Acoustic Modelling | 1 | 2.44% |
Voice Conversion | 1 | 2.44% |
Transliteration | 1 | 2.44% |
Zero-Shot Learning | 1 | 2.44% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |