File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Matrix product operator restricted Boltzmann machines

TitleMatrix product operator restricted Boltzmann machines
Authors
Issue Date2019
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000500
Citation
Proceedings of 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 14-19 July 2019 How to Cite?
AbstractA restricted Boltzmann machine (RBM) learns a probability distribution over its input samples and has numerous uses like dimensionality reduction, classification and generative modeling. Conventional RBMs accept vectorized data that dismiss potentially important structural information in the original tensor (multi-way) input. Matrix-variate and tensor-variate RBMs, named MvRBM and TvRBM, have been proposed but are all restrictive by model construction and have weak model expression power. This work presents the matrix product operator RBM (MPORBM) that utilizes a tensor network generalization of Mv/TvRBM, preserves input formats in both the visible and hidden layers, and results in higher expressive power. A novel training algorithm integrating contrastive divergence and an alternating optimization procedure is also developed. Numerical experiments compare the MPORBM with the traditional RBM and MvRBM for data classification and image completion and denoising tasks. The expressive power of the MPORBM as a function of the MPO-rank is also investigated.
Persistent Identifierhttp://hdl.handle.net/10722/275279
ISBN

 

DC FieldValueLanguage
dc.contributor.authorChen, C-
dc.contributor.authorBatselier, K-
dc.contributor.authorKo, CY-
dc.contributor.authorWong, N-
dc.date.accessioned2019-09-10T02:39:18Z-
dc.date.available2019-09-10T02:39:18Z-
dc.date.issued2019-
dc.identifier.citationProceedings of 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 14-19 July 2019-
dc.identifier.isbn978-1-7281-1986-1-
dc.identifier.urihttp://hdl.handle.net/10722/275279-
dc.description.abstractA restricted Boltzmann machine (RBM) learns a probability distribution over its input samples and has numerous uses like dimensionality reduction, classification and generative modeling. Conventional RBMs accept vectorized data that dismiss potentially important structural information in the original tensor (multi-way) input. Matrix-variate and tensor-variate RBMs, named MvRBM and TvRBM, have been proposed but are all restrictive by model construction and have weak model expression power. This work presents the matrix product operator RBM (MPORBM) that utilizes a tensor network generalization of Mv/TvRBM, preserves input formats in both the visible and hidden layers, and results in higher expressive power. A novel training algorithm integrating contrastive divergence and an alternating optimization procedure is also developed. Numerical experiments compare the MPORBM with the traditional RBM and MvRBM for data classification and image completion and denoising tasks. The expressive power of the MPORBM as a function of the MPO-rank is also investigated.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000500-
dc.relation.ispartofInternational Joint Conference on Neural Networks (IJCNN)-
dc.rightsInternational Joint Conference on Neural Networks (IJCNN). Copyright © IEEE.-
dc.rights©2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.titleMatrix product operator restricted Boltzmann machines-
dc.typeConference_Paper-
dc.identifier.emailWong, N: nwong@eee.hku.hk-
dc.identifier.authorityWong, N=rp00190-
dc.identifier.doi10.1109/IJCNN.2019.8851877-
dc.identifier.hkuros304918-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats