Transactions of The Japanese Society of Irrigation, Drainage and Rural Engineering
Online ISSN : 1884-7242
Print ISSN : 1882-2789
ISSN-L : 1882-2789
Learning Algorithm for Artificial Neural Networks by Extended Bayesian Method
Vbrification on some geotechnical engineering Problems
Noriyuki KOBAYASHIYoshitaka YOSHITAKEKeisuke TAKEDAKeiko MAEKAWA
Author information
JOURNALS FREE ACCESS

2008 Volume 2008 Issue 258 Pages 493-499,a1

Details
Abstract

One of the representative algorithms for learning of an artificial neural networks (ANN) is the back propagation method. But, it is sometimes difficult to converge and learn efficiently, because it minimizes the error function of the outputs for each learning data set in order and not simultaneously. In order to minimize the error functions for all learning data sets simultaneously, a new learning algorithm is proposed using the extended Bayesian method. However, a dificult but important problem in this method is to determine optimally the number of hidden layer units Lm for ANN and the parameter λ2 for the extended Bayesian method. Thus, the determination method of optimal λ2 and Lm by Akaike Bayesian information criteria is proposed. As a result of having applied it to consolidation and seismic problems, it is comparatively clear that the proposed method has faster convergence and higher learning capability.

Information related to the author
© The Japanese Society of Irrigation, Drainage and Rural Engineering
Previous article Next article
feedback
Top