Approximate learning algorithm for restricted boltzmann machines

Muneki Yasuda, Kazuyuki Tanaka

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

5 Citations (Scopus)

Abstract

A restricted Boltzmann machine consists of a layer of visible units and a layer of hidden units with no visible-visible or hidden-hidden connections. The restricted Boltzmann machine is the main component used in building up the deep belief network and has been studied by many researchers. However, the learning algorithm for the restricted Boltzmann machine is a NP-hard problem in general. In this paper we propose a new approximate learning algorithm for the restricted Boltzmann machines using the EM algorithm and the loopy belief propagation.

Original languageEnglish
Title of host publication2008 International Conference on Computational Intelligence for Modelling Control and Automation, CIMCA 2008
Pages692-697
Number of pages6
DOIs
Publication statusPublished - 2008 Dec 1
Event2008 International Conference on Computational Intelligence for Modelling Control and Automation, CIMCA 2008 - Vienna, Austria
Duration: 2008 Dec 102008 Dec 12

Publication series

Name2008 International Conference on Computational Intelligence for Modelling Control and Automation, CIMCA 2008

Other

Other2008 International Conference on Computational Intelligence for Modelling Control and Automation, CIMCA 2008
CountryAustria
CityVienna
Period08/12/1008/12/12

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Software
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Approximate learning algorithm for restricted boltzmann machines'. Together they form a unique fingerprint.

Cite this