Recurrent Batch NormalizationDownload PDF

Published: 21 Jul 2022, Last Modified: 22 Oct 2023ICLR 2017 PosterReaders: Everyone
Abstract: We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks. Whereas previous works only apply batch normalization to the input-to-hidden transformation of RNNs, we demonstrate that it is both possible and beneficial to batch-normalize the hidden-to-hidden transition, thereby reducing internal covariate shift between time steps. We evaluate our proposal on various sequential problems such as sequence classification, language modeling and question answering. Our empirical results show that our batch-normalized LSTM consistently leads to faster convergence and improved generalization.
TL;DR: Make batch normalization work in recurrent neural networks
Conflicts: umontreal.ca, google.com
Keywords: Deep learning, Optimization
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:1603.09025/code)
16 Replies

Loading