An Improved Levenberg-Marquardt Learning Algorithm for Neural Networks Based on Terminal Attractors

摘要：

In this paper, an improved Levenberg-Marquardt learning algorithm based on terminal attractors for feedforward neural networks is proposed. The effectiveness of the proposed algorithm in improving learning speed is shown by the simulation results.

作者: Batsukh Batbayar Xinghuo Yu

作者单位: School of Electrical and Computer Engineering,RMIT University,Melbourne VIC 3001 Australia

会议类型: 国际会议

会议名称: The 2nd International Symposium on Systems and Control in Aeronautics and Astronautics(第二届航空航天系统与控制国际会议 ISSCAA 2008)

会议地点: 深圳

会议语种:英文

页码: 333-336

在线出版日期: 2008-12-10（万方平台首次上网日期，不代表论文的发表时间）