Incremental neural networks for function approximation
Details
Serval ID
serval:BIB_84D9B8745359
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Incremental neural networks for function approximation
Journal
Nuclear Instruments and Methods in Physics Research Section A - Accelerators, Spectrometers, Detectors, and Associated Equipment
ISSN-L
0168-9002
Publication state
Published
Issued date
1997
Peer-reviewed
Oui
Volume
389
Pages
268-270
Language
english
Notes
5th International Workshop on Software Engineering, Neural Nets, Genetic Algorithms, Expert Systems, Symbolic Algebra and Automatic Calculations in Physics Research (AIHENP 96), LAUSANNE, SWITZERLAND, SEP 02-06, 1996
Abstract
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.
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.
Create date
07/10/2012 15:53
Last modification date
20/08/2019 14:44
Usage data
