点击次数：

论文类型：会议论文

发表时间：2008-01-01

收录刊物：CPCI-S

页面范围：264-268

关键字：Batch Gradient Method; Feedfoward Neural Network; Boundedness; Penalty

摘要：This paper considers a batch gradient method with penalty for training feedforward neural networks. The role of the penalty term is to control the magnitude of the weights and to improve the generalization performance of the network. A usual penalty is considered, which is a term proportional to the norm of the weights. The boundedness of the network is proved. The bounded ness is assumed as a precondition in an existing convergence result, and thus our result improves this convergence result.