点击次数：

论文类型：期刊论文

发表时间：2008-09-01

发表刊物：APPLIED MATHEMATICS AND MECHANICS-ENGLISH EDITION

收录刊物：SCIE、EI、Scopus

卷号：29

期号：9

页面范围：1231-1238

ISSN号：0253-4827

关键字：Elman network; gradient learning algorithm; convergence; monotonicity

摘要：The gradient method for training Elman networks with a finite training sample set is considered. Monotonicity of the error function in the iteration is shown. Weak and strong convergence results are proved, indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point, respectively. A numerical example is given to support the theoretical findings.