| 改进QDPSO算法在BP网络训练中的应用 |
| |
| 引用本文： | 熊伟丽,徐保国,孙俊.改进QDPSO算法在BP网络训练中的应用[J].系统仿真学报,2005,17(9):2078-2081. |
| |
| 作者姓名： | 熊伟丽 徐保国 孙俊 |
| |
| 作者单位： | 1. 江南大学控制科学与工程研究中心,江苏无锡,214122
2. 江南大学信息工程学院,江苏无锡,214122 |
| |
| 基金项目： | 国家自然科学基金（60474030） |
| |
| 摘 要： | QDPSO（Quantum Delta-Potential-Well-based Particle Swarm Optimization）算法是基于量子空间的粒子群算法，对QDPSO算法进行了改进，结合Iris分类问题，应用到BP网络的权值优化中，并和基于标准PSO算法的方法进行了比较。实验结果表明：该算法性能优于所比较的两种算法，并且具有良好的收敛性和稳定性。
|
| 关 键 词： | 神经网络 PSO算法 QDPSO算法 优化 |
| 文章编号： | 1004-731X（2005）09-2078-04 |
| 收稿时间： | 2005-01-10 |
| 修稿时间： | 2005-05-07 |
BP Network Learning Algorithm Based on Improved QDPSO |
| |
| XIONG Wei-li,XU Bao-guo,SUN Jun.BP Network Learning Algorithm Based on Improved QDPSO[J].Journal of System Simulation,2005,17(9):2078-2081. |
| |
| Authors: | XIONG Wei-li XU Bao-guo SUN Jun |
| |
| Institution: | 1.Control Science and Engineering Research Center, Southern Yangtze University, Wuxi 214122, China; 2. School of Information Engineering, Southern Yangtze University, Wuxi 214122, China |
| |
| Abstract: | QDPSO is the particle swarm optimization in quantum space. It was improved and applied in BP neural network training combining with Iris-classify problem. The proposed algorithm compared with that of which was based on the standard PSO. The results show that the proposed algorithm is superior to the other two algorithms with a better astringency and stability. |
| |
| Keywords: | Neural network Particle swarm optimization Quantum Delta-Potential-Well-based Particle swarm optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
