Open access
Date
2017-08-06Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
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 Short-Term 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 step-to-step 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 word-level 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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000233981Publication status
publishedExternal links
Book title
Proceedings of the 34 th International Conference on Machine LearningJournal / series
Proceedings of Machine Learning ResearchVolume
Pages / Article No.
Publisher
PMLREvent
Organisational unit
02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.09574 - Frazzoli, Emilio / Frazzoli, Emilio
More
Show all metadata
ETH Bibliography
yes
Altmetrics