Hits:

Indexed by:期刊论文

Date of Publication:2008-01-01

Journal:NEURAL NETWORK WORLD

Included Journals:SCIE、EI、Scopus

Volume:18

Issue:3

Page Number:171-180

ISSN No.:1210-0552

Key Words:Elman network; approximated gradient method; convergence

Abstract:An approximated gradient method for training Elman networks is considered. For the finite sample set, the error function is proved to be monotone in the training process, and the approximated gradient of the error function tends to zero if the weights sequence is bounded. Furthermore, after adding a moderate condition, the weights sequence itself is also proved to be convergent. A numerical example is given to support the theoretical findings.