Combined genetic algorithm optimization and regularized orthogonal least squares learning for radial basis function networks

Author

Chen, S. ; Wu, Y. ; Luk, B.L.

Author_Institution

Dept. of Electr. & Comput. Sci., Southampton Univ., UK

Volume

10

Issue

5

fYear

1999

fDate

9/1/1999 12:00:00 AM

Firstpage

1239

Lastpage

1243

Abstract

Presents a two-level learning method for radial basis function (RBF) networks. A regularized orthogonal least squares (ROLS) algorithm is employed at the lower level to construct RBF networks while the two key learning parameters, the regularization parameter and the RBF width, are optimized using a genetic algorithm (GA) at the upper level. Nonlinear time series modeling and prediction is used as an example to demonstrate the effectiveness of this hierarchical learning approach

Keywords

genetic algorithms; learning (artificial intelligence); least squares approximations; radial basis function networks; time series; genetic algorithm optimization; hierarchical learning approach; nonlinear time series modeling; regularization parameter; regularized orthogonal least squares learning; two-level learning method; Computational efficiency; Cost function; Genetic algorithms; Helium; Learning systems; Least squares methods; Network topology; Neural networks; Predictive models; Radial basis function networks;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.788663

Filename

788663