An incremental learning algorithm for functional approximation

Abstract : 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.
Type de document :
Article dans une revue
Advances in Engineering Software, Elsevier, 2009, 40 (8), pp.725-730. 〈10.1016/j.advengsoft.2008.12.018〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00430288
Contributeur : Sylvain Contassot-Vivier <>
Soumis le : vendredi 6 novembre 2009 - 14:05:55
Dernière modification le : vendredi 6 juillet 2018 - 15:06:06

Identifiants

Citation

Jacques Bahi, Sylvain Contassot-Vivier, Marc Sauget. An incremental learning algorithm for functional approximation. Advances in Engineering Software, Elsevier, 2009, 40 (8), pp.725-730. 〈10.1016/j.advengsoft.2008.12.018〉. 〈inria-00430288〉

Partager

Métriques

Consultations de la notice

359