Evolving space-filling curves to distribute radial basis functions over an input space

Author

Whitehead, Bruce A. ; Choate, Timothy D.

Author_Institution

Univ. of Tennessee Space Inst., Tullahoma, TN, USA

Volume

5

Issue

1

fYear

1994

fDate

1/1/1994 12:00:00 AM

Firstpage

15

Lastpage

23

Abstract

An evolutionary neural network training algorithm is proposed for radial basis function (RBF) networks. The locations of basis function centers are not directly encoded in a genetic string, but are governed by space-filling curves whose parameters evolve genetically. This encoding causes each group of codetermined basis functions to evolve to fit a region of the input space. A network produced from this encoding is evaluated by training its output connections only. Networks produced by this evolutionary algorithm appear to have better generalization performance on the Mackey-Glass time series than corresponding networks whose centers are determined by k-means clustering

Keywords

feedforward neural nets; fractals; learning (artificial intelligence); time series; Mackey-Glass time series; codetermined basis functions; evolutionary neural network training algorithm; radial basis functions; space-filling curves; Computer networks; Computer science; Encoding; Evolutionary computation; Genetic algorithms; Genetic mutations; Humans; Neural networks; Training data;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.265957

Filename

265957