File(s) under permanent embargo
Tensor-variate restricted Boltzmann machines
conference contribution
posted on 2015-01-01, 00:00 authored by Tu Dinh Nguyen, Quoc-Dinh Phung, Truyen TranTruyen Tran, Svetha VenkateshSvetha VenkateshRestricted 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.
History
Event
AAAI Conference on Artificial Intelligence (29th : 2015 : Austin Texas)Volume
3Pagination
2887 - 2893Publisher
AAAI PressLocation
Austin, Tex.Place of publication
Palo Alto, Calif.Start date
2015-01-25End date
2015-01-30ISBN-13
9781577357018Language
engNotes
paper No: 2887Publication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2015, The AuthorsTitle of proceedings
AAAI 2015: The Proceedings of the 29th AAAI Conference on Artificial IntelligenceUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC