点击次数：

论文类型：期刊论文

发表时间：2008-01-01

发表刊物：NEURAL NETWORK WORLD

收录刊物：SCIE、EI、Scopus

卷号：18

期号：3

页面范围：171-180

ISSN号：1210-0552

关键字：Elman network; approximated gradient method; convergence

摘要：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.