Multiple-weight recurrent neural networks

Zhu Cao, Linlin Wang, Gerard De Melo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Recurrent neural networks (RNNs) have enjoyed great success in speech recognition, natural language processing, etc. Many variants of RNNs have been proposed, including vanilla RNNs, LSTMs, and GRUs. However, current architectures are not particularly adept at dealing with tasks involving multi-faceted contents, i.e., data with a bimodal or multimodal distribution. In this work, we solve this problem by proposing Multiple-Weight RNNs and LSTMs, which rely on multiple weight matrices to better mimic the human ability of switching between contexts. We present a framework for adapting RNN-based models and analyze the properties of this approach. Our detailed experimental results show that our model outperforms previous work across a range of different tasks and datasets.

Original languageAmerican English
Title of host publication26th International Joint Conference on Artificial Intelligence, IJCAI 2017
EditorsCarles Sierra
PublisherInternational Joint Conferences on Artificial Intelligence
Pages1483-1489
Number of pages7
ISBN (Electronic)9780999241103
DOIs
StatePublished - 2017
Event26th International Joint Conference on Artificial Intelligence, IJCAI 2017 - Melbourne, Australia
Duration: Aug 19 2017Aug 25 2017

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume0

Other

Other26th International Joint Conference on Artificial Intelligence, IJCAI 2017
Country/TerritoryAustralia
CityMelbourne
Period8/19/178/25/17

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Multiple-weight recurrent neural networks'. Together they form a unique fingerprint.

Cite this