,CONVERGENCE OF GRADIENT METHOD WITH MOMENTUM FOR BACK-PROPAGATION NEURAL NETWORKS

• 作 者: Wei Wu Naimin Zhang Zhengxue Li Long Li Yan Liu
• 机 构: Department of Applied Mathematics,Dalian University oy Technology,Dalian 116024,Chinarn“,”Mathematic
• 出 处: 计算数学（英文版）
• 发表日期: 2008年4期
• 关键词: Back-propagation(BP)neural networks Gradient method Momentum Convergence

In this work,a gradient method with momentum for BP neural networks is considered.The momentum coefficient is chosen in an adaptive manner to accelerate and stabilize the leaing procedure of the network weights.Corresponding convergence results are proved.