Regularization

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 Activations

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Speech Synthesis 14 33.33%
Text-To-Speech Synthesis 4 9.52%
Language Modelling 3 7.14%
Voice Cloning 2 4.76%
Style Transfer 2 4.76%
Acoustic Modelling 1 2.38%
Voice Conversion 1 2.38%
Transliteration 1 2.38%
Zero-Shot Learning 1 2.38%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories