Factored temporal sigmoid belief networks for sequence learning

Jiaming Song, Zhe Gan, Lawrence Carin

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

5 Scopus citations

Abstract

Deep conditional generative models are developed to simultaneously learn the temporal dependencies of multiple sequences. The model is designed by introducing a three-way weight tensor to capture the multiplicative interactions between side information and sequences. The proposed model builds on the Temporal Sigmoid Belief Network (TSBN), a sequential stack of Sigmoid Belief Networks (SBNs). The transition matrices are further factored to reduce the number of parameters and improve generalization. When side information is not available, a general framework for semi-supervised learning based on the proposed model is constituted, allowing robust sequence classification. Experimental results show that the proposed approach achieves state-of-theart predictive and classification performance on sequential data, and has the capacity to synthesize sequences, with controlled style transitioning and blending.
Original languageEnglish (US)
Title of host publication33rd International Conference on Machine Learning, ICML 2016
PublisherInternational Machine Learning Society (IMLS)rasmussen@ptd.net
Pages1937-1946
Number of pages10
ISBN (Print)9781510829008
StatePublished - Jan 1 2016
Externally publishedYes

Fingerprint Dive into the research topics of 'Factored temporal sigmoid belief networks for sequence learning'. Together they form a unique fingerprint.

Cite this