Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
Abstract
We propose zoneout, a novel 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. We perform an empirical investigation of various RNN regularizers, and find that zoneout gives significant performance improvements across tasks. We achieve competitive results with relatively simple models in character- and word-level language modelling on the Penn Treebank and Text8 datasets, and combining with recurrent batch normalization yields state-of-the-art results on permuted sequential MNIST.
Cite
Text
Krueger et al. "Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations." International Conference on Learning Representations, 2017.Markdown
[Krueger et al. "Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/krueger2017iclr-zoneout/)BibTeX
@inproceedings{krueger2017iclr-zoneout,
title = {{Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations}},
author = {Krueger, David and Maharaj, Tegan and Kramár, János and Pezeshki, Mohammad and Ballas, Nicolas and Ke, Nan Rosemary and Goyal, Anirudh and Bengio, Yoshua and Courville, Aaron C. and Pal, Christopher J.},
booktitle = {International Conference on Learning Representations},
year = {2017},
url = {https://mlanthology.org/iclr/2017/krueger2017iclr-zoneout/}
}