点击次数：

论文类型：期刊论文

发表时间：2009-06-01

发表刊物：NEURAL PROCESSING LETTERS

收录刊物：SCIE、EI、Scopus

卷号：29

期号：3

页面范围：205-212

ISSN号：1370-4621

关键字：Feedforward neural networks; Linear output; Online gradient method; Penalty; Boundedness; Convergence

摘要：This paper investigates an online gradient method with penalty for training feedforward neural networks with linear output. A usual penalty is considered, which is a term proportional to the norm of the weights. The main contribution of this paper is to theoretically prove the boundedness of the weights in the network training process. This boundedness is then used to prove an almost sure convergence of the algorithm to the zero set of the gradient of the error function.