| 基于IGA的多层神经网络BP算法及在系统辨识中的应用 |
| |
| 引用本文： | 张葛祥,唐钟.基于IGA的多层神经网络BP算法及在系统辨识中的应用[J].西南科技大学学报,2002,17(2):9-13. |
| |
| 作者姓名： | 张葛祥 唐钟 |
| |
| 作者单位： | 西南科技大学信息与控制工程学院,四川,绵阳,621002 |
| |
| 摘 要： | 本文针对用GA训练NN权值时 ,花费的代价随精度的提高而剧烈增加的缺陷 ,提出了一种利用IGA较强的全局搜索能力和IBPA较强的局部搜索能力的结合算法 ;先利用IGA优化多层前馈神经网络的权值 ,然后再用IBPA提高搜索精度 ,有效地避免了IBPA易陷入局部极小点和IGA过早收敛的缺点 ,实验结果表明 ,此算法是有效的
|
| 关 键 词： | 遗传算法 神经网络 BP算法 系统辨识 |
| 文章编号： | 1007-8916(2002)02-0009-05 |
| 修稿时间： | 2001年9月4日 |
A MULTI LAYER NEURAL NETWORK BACKPROPAGATION ALGORITHM BASED ON IMPROVED GENETIC ALGORITHM AND APPLICATION IN SYSTEM IDENTIFICATION |
| |
| Zhang Gexiang,Tang Zhong.A MULTI LAYER NEURAL NETWORK BACKPROPAGATION ALGORITHM BASED ON IMPROVED GENETIC ALGORITHM AND APPLICATION IN SYSTEM IDENTIFICATION[J].Journal of Southwest University of Science and Technology,2002,17(2):9-13. |
| |
| Authors: | Zhang Gexiang Tang Zhong |
| |
| Institution: | Southwest University of Scince and Technology |
| |
| Abstract: | In this paper, a combined algorithm of utilizing good global search of improved genetic algorithm and good local search of improved backpropagation algorithm is put forward aiming at the shortcoming of the cost rise steeply as the precision is improved when the weights of neural network are trained by use genetic algorithm; the weights of multi_layer feedforward neural network are optimized by using improved genetic algorithm and then search precision is increased by using improved backpropagation algorithm, thus, lost in local minimum of IBPA easily and premature convergence of IGA are avoided effectively. The algorithm is good through experiments. |
| |
| Keywords: | genetic algorithm neural network BP algorithm system identification |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
