Minimal training set size estimation for neural network-based function approximation

Author

Malinowski, Aleksander ; Zurada, Jacek M. ; Aronhime, Peter B.

Author_Institution

Dept. of Electr. Eng., Louisville Univ., KY, USA

Volume

6

fYear

1994

fDate

30 May-2 Jun 1994

Firstpage

403

Abstract

A new approach to the problem of n-dimensional continuous and sampled-data function approximation using a two-layer neural network is presented. The generalized Nyquist theorem is introduced to solve for the optimum number of training examples in n-dimensional input space. Choosing the smallest but still sufficient set of training vectors results in a reduced learning time for the network. Analytical formulas and algorithm for training set size reduction are developed and illustrated by two-dimensional data examples

Keywords

function approximation; learning (artificial intelligence); minimisation; neural nets; sampled data systems; Nyquist theorem; algorithm; continuous data; function approximation; learning time; minimal training set size; sampled data; two-dimensional data; two-layer neural network; Electronic mail; Fourier transforms; Frequency estimation; Function approximation; Multi-layer neural network; Multidimensional systems; Neural networks; Sampling methods; Signal restoration; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on

Conference_Location

London

Print_ISBN

0-7803-1915-X

Type

conf

DOI

10.1109/ISCAS.1994.409611

Filename

409611