点击次数：

论文类型：期刊论文

发表时间：2009-06-01

发表刊物：IEEE TRANSACTIONS ON NEURAL NETWORKS

收录刊物：SCIE、EI、PubMed

卷号：20

期号：6

页面范围：1050-1054

ISSN号：1045-9227

关键字：Boundedness; convergence; feedforward neural networks; online gradient method; penalty

摘要：In this brief, we consider an online gradient method with penalty for training feedforward neural networks. Specifically, the penalty is a term proportional to the norm of the weights. Its roles in the method are to control the magnitude of the weights and to improve the generalization performance of the network. By proving that the weights are automatically bounded in the network training with penalty, we simplify the conditions that are required for convergence of online gradient method in literature. A numerical example is given to support the theoretical analysis.