Recurrent Highway Networks
[edit]
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:41894198, 2017.
Abstract
Many sequential processing tasks require complex nonlinear transition functions from one step to the next. However, recurrent neural networks with “deep” transition functions remain difficult to train, even when using Long ShortTerm Memory (LSTM) networks. We introduce a novel theoretical analysis of recurrent networks based on Gersgorin’s circle theorem that illuminates several modeling and optimization issues and improves our understanding of the LSTM cell. Based on this analysis we propose Recurrent Highway Networks, which extend the LSTM architecture to allow steptostep transition depths larger than one. Several language modeling experiments demonstrate that the proposed architecture results in powerful and efficient models. On the Penn Treebank corpus, solely increasing the transition depth from 1 to 10 improves wordlevel perplexity from 90.6 to 65.4 using the same number of parameters. On the larger Wikipedia datasets for character prediction (text8 and enwik8), RHNs outperform all previous results and achieve an entropy of 1.27 bits per character.
Related Material


