Home >

news Help

Publication Information


Title
Japanese: 
English:Asymptotic Behavior of Stochastic Complexity of Complete Bipartite Graph-type Boltzmann Machines 
Author
Japanese: 西山悠, 渡邊澄夫.  
English: YU NISHIYAMA, SUMIO WATANABE.  
Language English 
Journal/Book name
Japanese: 
English:LNCS 4232 
Volume, Number, Page         pp. 671-678
Published date Oct. 2006 
Publisher
Japanese: 
English:Springer 
Conference name
Japanese: 
English:ICONIP 
Conference site
Japanese: 
English:China 
DOI https://doi.org/10.1007/11893028_47
Abstract In singular statistical models, it was shown that Bayes learning is effective. However, on Bayes learning, calculation containing the Bayes posterior distribution requires huge computational costs. To overcome the problem, mean field approximation (or equally variational Bayes method) was proposed. Recently, the generalization error and stochastic complexity in mean field approximation have been theoretically studied. In this paper, we treat the complete bipartite graph-type Boltzmann machines and derive the upper bound of the asymptotic stochastic complexity in mean field approximation.

©2007 Tokyo Institute of Technology All rights reserved.