| Multilayered feed forward neural network based on particle swarmopti mizer algorithm |
| |
| 引用本文： | 潘峰,陈杰,涂序彦,付继伟. Multilayered feed forward neural network based on particle swarmopti mizer algorithm[J]. 系统工程与电子技术(英文版), 2005, 16(3) |
| |
| 作者姓名： | 潘峰 陈杰 涂序彦 付继伟 |
| |
| 作者单位： | Dept .of Automatic Control，School of Information Science and Technology，Beijing Inst .of Technology，Dept .of Automatic Control，School of Information Science and Technology，Beijing Inst .of Technology，Dept .of Automatic Control，School of Information Science and Technology，Beijing Inst .of Technology，Dept .of Automatic Control，School of Information Science and Technology，Beijing Inst .of Technology Beijing 100081，P. R. China，Beijing 100081，P. R. China，Beijing 100081，P. R. China，Beijing 100081，P. R. China |
| |
| 摘 要： | 1 .INTRODUCTIONNowadays there are many algorithms used to trainand opti mize neural network.BPalgorithm,whichisbased on gradient vectors of nodes ,is the most popu-lar neural network training method. Once gradient in-formation is obtained, kinds of regression technologiesbased on gradient can be adopt to update parameters.However BP algorithm faces some problems :(1) speed of convergence ; (2) local mini ma ; (3)sensitivity of initial value ;(4) dependence on gradi-ent information. For s…
|
Multilayered feed forward neural network based on particle swarm optimizer algorithm |
| |
| Pan Feng,Chen Jie,Tu Xuyan,Fu Jiwei. Multilayered feed forward neural network based on particle swarm optimizer algorithm[J]. Journal of Systems Engineering and Electronics, 2005, 16(3) |
| |
| Authors: | Pan Feng Chen Jie Tu Xuyan Fu Jiwei |
| |
| Affiliation: | Dept.of Automatic Control,School of Information Science and Technology,Beijing Inst.of Technology,Beijing 100081,P.R.China |
| |
| Abstract: | BP is a commonly used neural network training method, which has some disadvantages, such as local minima, sensitivity of initial value of weights, total dependence on gradient information. This paper presents some methods to train a neural network, including standard particle swarm optimizer (PSO), guaranteed convergence particle swarm optimizer (GCPSO), an improved PSO algorithm, and GCPSO BP, an algorithm combined GCPSO with BP. The simulation results demonstrate the effectiveness of the three algorithms for neural network training. |
| |
| Keywords: | BP PSO guaranteed convergence particle swarm optimizer (GCPSO) GCPSO BP. |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
