You are not logged in.
Openly accessible

Tensor-variate restricted Boltzmann machines

Nguyen, Tu Dinh, Tran, Truyen, Phung, Dinh and Venkatesh, Svetha 2015, Tensor-variate restricted Boltzmann machines, in AAAI 2015: The Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI Press, Palo Alto, Calif., pp. 2887-2893.

Attached Files
Name Description MIMEType Size Downloads
nguyen-td-tensorvariate-2015.pdf Published version application/pdf 2.56MB 10

Title Tensor-variate restricted Boltzmann machines
Author(s) Nguyen, Tu Dinh
Tran, TruyenORCID iD for Tran, Truyen orcid.org/0000-0001-6531-8907
Phung, DinhORCID iD for Phung, Dinh orcid.org/0000-0002-9977-8247
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Conference name AAAI Conference on Artificial Intelligence (29th : 2015 : Austin Texas)
Conference location Austin, Tex.
Conference dates 25-30 Jan. 2015
Title of proceedings AAAI 2015: The Proceedings of the 29th AAAI Conference on Artificial Intelligence
Publication date 2015
Start page 2887
End page 2893
Total pages 7
Publisher AAAI Press
Place of publication Palo Alto, Calif.
Keyword(s) tensor
rbm
restricted boltzmann machine
tvrbm
multiplicative interaction
eeg
Summary Restricted Boltzmann Machines (RBMs) are an important class of latent variable models for representing vector data. An under-explored area is multimode data, where each data point is a matrix or a tensor. Standard RBMs applying to such data would require vectorizing matrices and tensors, thus resulting in unnecessarily high dimensionality and at the same time, destroying the inherent higher-order interaction structures. This paper introduces Tensor-variate Restricted Boltzmann Machines (TvRBMs) which generalize RBMs to capture the multiplicative interaction between data modes and the latent variables. TvRBMs are highly compact in that the number of free parameters grows only linear with the number of modes. We demonstrate the capacity of TvRBMs on three real-world applications: handwritten digit classification, face recognition and EEG-based alcoholic diagnosis. The learnt features of the model are more discriminative than the rivals, resulting in better classification performance.
Notes paper No: 2887
ISBN 9781577357018
Language eng
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2015, The Authors
Persistent URL http://hdl.handle.net/10536/DRO/DU:30076888

Document type: Conference Paper
Collections: Centre for Pattern Recognition and Data Analytics
Open Access Collection
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 2 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 148 Abstract Views, 12 File Downloads  -  Detailed Statistics
Created: Tue, 01 Mar 2016, 14:28:39 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.