An incremental learning algorithm for function approximation

This paper presents an incremental learning algorithm for feed-forward neural networks used as approximators of real world data. This algorithm allows neural networks of limited size to be obtained, providing better performances. The algorithm is compared to two of the main incremental algorithms (D...

Full description

Saved in:
Bibliographic Details
Published in:Advances in engineering software (1992) 2009-08, Vol.40 (8), p.725-730
Main Authors: Bahi, Jacques M., Contassot-Vivier, Sylvain, Sauget, Marc
Format: Article
Language:English
Subjects:
Function approximation
Incremental learning
Neural networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents an incremental learning algorithm for feed-forward neural networks used as approximators of real world data. This algorithm allows neural networks of limited size to be obtained, providing better performances. The algorithm is compared to two of the main incremental algorithms (Dunkin and cascade correlation) in the respective contexts of synthetic data and of real data consisting of radiation doses in homogeneous environments.
ISSN:0965-9978
DOI:10.1016/j.advengsoft.2008.12.018