| ELM-RBF神经网络的智能优化策略 |
| |
| 引用本文： | 李彬,李贻斌,荣学文.ELM-RBF神经网络的智能优化策略[J].山东大学学报(理学版),2010,45(5):48-51. |
| |
| 作者姓名： | 李彬 李贻斌 荣学文 |
| |
| 作者单位： | 1. 山东大学控制科学与工程学院,山东,济南,250061;山东轻工业学院数理学院,山东,济南,250353
2. 山东大学控制科学与工程学院,山东,济南,250061 |
| |
| 基金项目： | 国家自然科学基金资助项目，山东省重点基金资助项目 |
| |
| 摘 要： | 提出了ELM-RBF(extreme learning machine-radial basis function)神经网络的智能优化方法,采用差分进化算法和粒子群优化算法来确定ELM-RBF神经网络中隐层神经元的中心和宽度。仿真结果表明,在具有相同的网络结构前提下,基于智能优化策略的ELM-RBF神经网络学习算法具有更好的泛化能力和较好的鲁棒性。
|
| 关 键 词： | 径向基函数神经网络 智能优化 差分进化算法 粒子群优化算法 |
| 收稿时间： | 2009-12-13 |
Intelligent optimization strategy for ELM-RBF neural networks |
| |
| LI Bin,LI Yi-bin,RONG Xue-wen.Intelligent optimization strategy for ELM-RBF neural networks[J].Journal of Shandong University,2010,45(5):48-51. |
| |
| Authors: | LI Bin LI Yi-bin RONG Xue-wen |
| |
| Institution: | 1.School of Control Science and Engineering, Shandong University, Jinan 250061, Shandong, China;
2. College of Mathematical and Physical Sciences, Shandong Institute of Light Industry, Jinan 250353, Shandong, China |
| |
| Abstract: | A method of intelligent optimization strategy for extreme learning machine-radial basis function (ELM-RBF) neural networks was proposed, in which the centers and impact widths of hidden neural kernels were determined by the intelligent optimization algorithms of differential evolution and particle swarm optimization. Simulation results showed that the ELM-RBF neural networks learning algorithm based on the intelligent optimization strategy could generate much better generalization performance and robustness than other algorithms with the same network architecture. |
| |
| Keywords: | radial basis function neural networks intelligent optimization differential evolution algorithm particle swarm optimization algorithm |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《山东大学学报(理学版)》浏览原始摘要信息 |
| 点击此处可从《山东大学学报(理学版)》下载免费的PDF全文 |
|
