Incremental neural networks for function approximation

被引：5

作者：

Chentouf, R

Jutten, C

Maignan, M

Kanevsky, M

机构：

[1] UNIV LAUSANNE,CH-1015 LAUSANNE,SWITZERLAND

[2] INST NUCL SAFETY,MOSCOW 113191,RUSSIA

来源：

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT | 1997年 / 389卷 / 1-2期

关键词：

function approximation; adding neurons; adding layers; model comparison; stopping criterion;

D O I：

10.1016/S0168-9002(97)00081-8

中图分类号：

TH7 [仪器、仪表];

学科分类号：

0804 ; 080401 ; 081102 ;

摘要：

A new strategy for incremental building of multilayer feedforward neural networks is proposed in the context of approximation of functions from R-p to R-q using noisy data. A stopping criterion based on the properties of the noise is also proposed. Experimental results for both artificial and real data are performed and two alternatives of the proposed construction strategy are compared.

引用

页码：268 / 270

页数：3