期刊文献+

自构造RBF神经网络及其参数优化 被引量:11

Self-growing RBF Neural Networks and Parameters Optimization
下载PDF
导出
摘要 径向基函数神经网络的构造需要确定每个RBF的中心、宽度和数目。该文利用改进的聚类算法自动构造RBFN,考虑样本的类别属性,根据样本分布自动计算RBF的中心和宽度,并确定RBF的数目。所有的网络参数采用非线性优化算法来优化。通过IRIS分类问题和混沌时间序列预测评价自构建RBFN的性能,验证参数优化效果。结果表明,自构造RBFN不但能够自动确定网络结构,而且具有良好的模式分类和函数逼近能力。通过对网络参数的非线性优化,该算法明显改善了网络性能。 Construction of Radiai Basis Function Neural(RBFN) networks involves computation of centers, widths of each RBF, and number of RBF in the middle layer. The modified clustering algorithm is used to construct RBFN automaticaily. The algorithm considers the class membership of training samples, can automaticai!y compute RBF centers and widths, and determines the number of Radiai Basis Function(RBF) units based on the distribution of samples. Parameters are optimized with nonlinear optimization technique. The performance Of the self-growing RBFN and effects of the optimization are estimated with IRIS classification problem and chaotic time series prediction. The results confirm that self-growing RBFN determines networks structure automatically, and has good performance in pattern recognition and function approximation. Better performance can be observed after nonlinear optimization of networks parameters.
出处 《计算机工程》 CAS CSCD 北大核心 2008年第9期200-202,共3页 Computer Engineering
关键词 径向基函数 自构造网络 参数优化 模式识别 混沌时间序列 Radial Basis Function(RBF) self-growing networks parameter optimization pattern recognition chaotic time series
  • 相关文献

参考文献6

  • 1刘昆,颜钢锋.基于模糊RBF神经网络的函数逼近[J].计算机工程,2001,27(2):70-71. 被引量:16
  • 2Wan Chuanhao.Self-configuring Radial Basis Function Neural Networks for Chemical Pattern Recognition[J].Journal Chem.Inf.Comput.Sci.,1999,39(6):1049-1056. 被引量:1
  • 3Choi S W,Lee D,Park J H.Nonlinear Regression Using RBFN with Linear Submodels[J].Chemometrics and Intelligent Laboratory Systems,2003,65(2):191-208. 被引量:1
  • 4Schwenker F,Kestler H A,Palm G.Three Learning Phases for Radial-basis-function Networks[J].Neural Networks,2001,14(4/5):439-458. 被引量:1
  • 5Magoulas G D,Vrahatis M N,Androulakis G S.Effective Backpropagation Training with Variable Stepsize[J].Neural Networks,1997,10(1):69-82. 被引量:1
  • 6赵温波,黄德双.全结构遗传优化径向基概率神经网络[J].红外与毫米波学报,2004,23(2):113-118. 被引量:4

二级参考文献9

  • 1沈清.神经网络应用技术[M].长沙:国防科技大学出版社,1993.. 被引量:52
  • 2徐秉铮,神经网络与应用,1994年 被引量:1
  • 3沈清,神经网络应用技术,1993年 被引量:1
  • 4Huang D S. Radial basis probabilistic neural networks:Model and application [J]. International Journal of Pattern Recognition and Artificial Intelligence, 1999, 13 ( 7 ):1083-1101 被引量:1
  • 5Lowe D. Adaptive radial basis function nonlinearities and the problem of generalization[A]. London: In proceeding of First International Conference on Artifcial Neural Networks,1989, 171-175 被引量:1
  • 6Specht D E. Probabilistic neural networks [J]. Neural Networks, 1990, 109-118 被引量:1
  • 7Zhou Z H, Chen S F, Chen Z Q. A Fast Adaptive Neural Network Classifier[ J]. FANNC: Knowledge and Information Systems, 2000, 115-129 被引量:1
  • 8Zhao W B, Huang D S. The structure optimization of radial basis probabilistic neural networks based on genetic algorithms [ A ]. Hawaii: In proceeding of International Joint conference on Neural Networks 2002, 1086-1091 被引量:1
  • 9Fisher R A. The use of multiple measurements in taxonomic problems[J]. Annals of Eugenics, 1936,7:179-188 被引量:1

共引文献18

同被引文献79

引证文献11

二级引证文献55

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部