|
|||||
|
|
An improved training algorithm for feedforward neural network learning based on terminal attractors |
|
| Authors: | Xinghuo Yu Bin Wang Batsukh Batbayar Liuping Wang Zhihong Man |
| Institution: | 1.Platform Technologies Research Institute,RMIT University,Melbourne,Australia;2.School of Automation,Southeast University,Nanjing,China;3.School of Electrical and Computer Engineering,RMIT University,Melbourne,Australia;4.School of Information Technology,National University of Mongolia,Ulaanbaatar,Mongolia;5.Faculty of Engineering and Industrial Sciences,Swinburne University of Technology,Melbourne,Australia |
| Abstract: | In this paper, an improved training algorithm based on the terminal attractor concept for feedforward neural network learning is proposed. A condition to avoid the singularity problem is proposed. The effectiveness of the proposed algorithm is evaluated by various simulation results for a function approximation problem and a stock market index prediction problem. It is shown that the terminal attractor based training algorithm performs consistently in comparison with other existing training algorithms. |
| Keywords: | |
| 本文献已被 SpringerLink 等数据库收录！ | |