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 | 12 | 44.44% |
Text-To-Speech Synthesis | 3 | 11.11% |
Language Modelling | 3 | 11.11% |
Style Transfer | 2 | 7.41% |
General Classification | 1 | 3.70% |
Speaker Verification | 1 | 3.70% |
Speech Recognition | 1 | 3.70% |
Meta-Learning | 1 | 3.70% |
Disentanglement | 1 | 3.70% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |