点击次数：

论文类型：期刊论文

发表时间：2009-01-01

发表刊物：DISCRETE DYNAMICS IN NATURE AND SOCIETY

收录刊物：SCIE、Scopus

卷号：2009

ISSN号：1026-0226

摘要：The batch split-complex backpropagation (BSCBP) algorithm for training complex-valued neural networks is considered. For constant learning rate, it is proved that the error function of BSCBP algorithm is monotone during the training iteration process, and the gradient of the error function tends to zero. By adding a moderate condition, the weights sequence itself is also proved to be convergent. A numerical example is given to support the theoretical analysis. Copyright (C) 2009 Huisheng Zhang et al.