| 一种改进的RBF神经网络多目标优化算法 |
| |
| 引用本文： | 肖忠良,李智勇,贾宜. 一种改进的RBF神经网络多目标优化算法[J]. 科学技术与工程, 2009, 9(21) |
| |
| 作者姓名： | 肖忠良 李智勇 贾宜 |
| |
| 作者单位： | 湖南大学,计算机与通信学院,长沙,410082;湖南娄底职业技术学院,电子信息工程系,娄底,417000;湖南大学,计算机与通信学院,长沙,410082 |
| |
| 摘 要： | 针对RBF网络训练中的多目标优化问题,提出了一种基于Pareto方法的改进的非支配排序遗传算法INSGA(Improved Non-dominated Sorting Genetic Algorithm).通过对某企业的订单数据进行预测的实验结果表明,它可以有效地解决以训练误差和测试误差为优化准则的RBF网络的参数确定问题,验证了改进的NSGA算法与RBF网络结合的可行性.
|
| 关 键 词： | 多目标优化 非支配排序 遗传算法 RBF网络优化 |
| 收稿时间： | 2009-08-03 |
| 修稿时间： | 2009-08-18 |
An Improved Multi-Objective Optimization Algorithm for RBF Neural Network |
| |
| xiao zhongliang,LI Zhi-yong and Jia Yi. An Improved Multi-Objective Optimization Algorithm for RBF Neural Network[J]. Science Technology and Engineering, 2009, 9(21) |
| |
| Authors: | xiao zhongliang LI Zhi-yong Jia Yi |
| |
| Affiliation: | ollege of Computer and Communication, Hunan University,,School of Statistics ,Hunan University, Changsha 410082 |
| |
| Abstract: | This paper proposes an Improved Non-dominated Sorting Genetic Algorithm or INSGA aimed to the multi-objective optimization problem in RBF network. The experimental results of commerce order- predicting show that the new algorithm can effectively solve the parameters optimization problem of RBF network which the optimization criterions are composed of training error and testing error. |
| |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《科学技术与工程》浏览原始摘要信息 |
|
点击此处可从《科学技术与工程》下载全文 |
|
