TY - GEN
T1 - Approximate learning algorithm for restricted boltzmann machines
AU - Yasuda, Muneki
AU - Tanaka, Kazuyuki
PY - 2008/12/1
Y1 - 2008/12/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=70449555200&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70449555200&partnerID=8YFLogxK
U2 - 10.1109/CIMCA.2008.57
DO - 10.1109/CIMCA.2008.57
M3 - Conference contribution
AN - SCOPUS:70449555200
SN - 9780769535142
T3 - 2008 International Conference on Computational Intelligence for Modelling Control and Automation, CIMCA 2008
SP - 692
EP - 697
BT - 2008 International Conference on Computational Intelligence for Modelling Control and Automation, CIMCA 2008
T2 - 2008 International Conference on Computational Intelligence for Modelling Control and Automation, CIMCA 2008
Y2 - 10 December 2008 through 12 December 2008
ER -