Learning heterogeneous functions from sparse and non-uniform samples

Author

Pokrajac, Dragoljub ; Obradovic, Zoran

Author_Institution

Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA

Volume

3

fYear

2000

fDate

2000

Firstpage

103

Abstract

A boosting-based method for centers placement in radial basis function networks (RBFNs) is proposed. Also, the influence of several methods for drawing random samples on the accuracy of RBFNs is examined. The new method is compared to trivial, linear and non-linear regressors including the multilayer perceptron and alternative RBFN learning algorithms and its advantages are demonstrated for learning heterogeneous functions from sparse and non-uniform samples

Keywords

generalisation (artificial intelligence); learning (artificial intelligence); radial basis function networks; boosting-based method; centers placement; heterogeneous functions; learning algorithms; linear regressors; multilayer perceptron; nonlinear regressors; nonuniform samples; sparse samples; trivial regressors; Boosting; Computer science; Multilayer perceptrons; Neurons; Predictive models; Probability distribution; Radial basis function networks; Regression tree analysis; Sampling methods; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.861288

Filename

861288