A Parameter Adjustment Algorithm of BP Neural Network

摘要：

BP neural network converges slowly and usuallyfalls into partial minimum points.In this paper a newparameter adjustment algorithm is proposed,usinganterior accumulated information to modifymomentum.The algorithm has characteristics ofenhancing the network convergence rate,preventingvibration and reducing network errors.The simulationresult indicates that the algorithm is more effective.

作者: Li Xiaozhong Li Qiu

作者单位: College of Computer Science & Information Engineering,Tianjin University of Science & Technology,Tia College of Computer Science & Information Engineering,Tianjin University of Science & Technology,Tia

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 892-895

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）