点击次数：

论文类型：期刊论文

发表时间：2010-02-01

发表刊物：SOFT COMPUTING

收录刊物：SCIE、EI、Scopus

卷号：14

期号：3

页面范围：245-250

ISSN号：1432-7643

关键字：Fully recurrent neural network; Gradient descent learning algorithm; Convergence; Monotonicity

摘要：Recurrent neural networks have been successfully used for analysis and prediction of temporal sequences. This paper is concerned with the convergence of a gradient-descent learning algorithm for training a fully recurrent neural network. In literature, stochastic process theory has been used to establish some convergence results of probability nature for the on-line gradient training algorithm, based on the assumption that a very large number of (or infinitely many in theory) training samples of the temporal sequences are available. In this paper, we consider the case that only a limited number of training samples of the temporal sequences are available such that the stochastic treatment of the problem is no longer appropriate. Instead, we use an off-line gradient training algorithm for the fully recurrent neural network, and we accordingly prove some convergence results of deterministic nature. The monotonicity of the error function in the iteration is also guaranteed. A numerical example is given to support the theoretical findings.