首页 | 本学科首页   官方微博 | 高级检索  
     

基于改进的PSO算法的神经网络集成
引用本文:施彦,黄聪明,侯朝桢. 基于改进的PSO算法的神经网络集成[J]. 复旦学报(自然科学版), 2004, 43(5): 692-695
作者姓名:施彦  黄聪明  侯朝桢
作者单位:北京理工大学,化工与环境学院,北京,100081;北京理工大学,信息科学技术学院,北京,100081
摘    要:提出了一种新的神经网络集成结论生成方法,即基于可重复采样技术(Bootstrap)的粒子群优化(PSO)算法——BPSO算法,通过限制组合权值的范围来减小“多维共线性”的影响,还利用采样技术构造不同的适应度函数,增加“粒子”的多样性从而便于在一定范围内灵活调节组合权值,并减小噪声对集成的影响.实验表明。BPSO算法是优化组合权值的有效方法,提高了神经网络集成的泛化能力.

关 键 词:神经网络集成  组合权值优化  粒子群优化算法  可重复采样技术
文章编号:0427-7104(2004)05-0692-04

Neural Network Ensembles Based on Improved PSO Algorithm
SHI Yan,HUANG Cong-ming,HOU Chao-zhen. Neural Network Ensembles Based on Improved PSO Algorithm[J]. Journal of Fudan University(Natural Science), 2004, 43(5): 692-695
Authors:SHI Yan  HUANG Cong-ming  HOU Chao-zhen
Affiliation:SHI Yan~1,HUANG Cong-ming~1,HOU Chao-zhen~2
Abstract:An improved PSO algorithm based on Bootstrap named with BPSO for neural network ensembles is proposed. On the one side, the effect of collinearity is decreased by restricting the range of combination weights. On the other hand, different fitness functions are constructed on different data by using bootstrap technique, which increases the diversity of particles. In consequence combination weights are easier to be adjusted in a definite range and the effects of noise are decreased. Experiments results show that the BPSO algorithm is an effect ensemble method and improves the generalization ability of neural network ensembles.
Keywords:neural network ensembles  combination weights optimization  PSO algorithm  Bootstrap
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号