CUED Publications database

A theoretically grounded application of dropout in recurrent neural networks

Gal, Y and Ghahramani, Z (2016) A theoretically grounded application of dropout in recurrent neural networks. Advances in Neural Information Processing Systems. pp. 1027-1035. ISSN 1049-5258

Full text not available from this repository.

Abstract

© 2016 NIPS Foundation - All Rights Reserved. Recurrent neural networks (RNNs) stand at the forefront of many recent developments in deep learning. Yet a major difficulty with these models is their tendency to overfit, with dropout shown to fail when applied to recurrent layers. Recent results at the intersection of Bayesian modelling and deep learning offer a Bayesian interpretation of common deep learning techniques such as dropout. This grounding of dropout in approximate Bayesian inference suggests an extension of the theoretical results, offering insights into the use of dropout with RNN models. We apply this new variational inference based dropout technique in LSTM and GRU models, assessing it on language modelling and sentiment analysis tasks. The new approach outperforms existing techniques, and to the best of our knowledge improves on the single model state-of-the-art in language modelling with the Penn Treebank (73.4 test perplexity). This extends our arsenal of variational tools in deep learning.

Item Type: Article
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:26
Last Modified: 16 Nov 2017 02:28
DOI: