`Recruiting Neural-Gas' for function approximation

Michael Aupetit, Pierre Couturier, Pierre Massotte

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A new algorithm for function approximation with an artificial neural network is presented. It is based on Neural-Gas networks which combine self-organization of the neurons in the input space arid supervised learning of the output values according to the function to approximate. In that paper, the original learning rule of the input weights is modified to take into account the output error. The neurons with a greater error tend to `recruit' their neighbors to help them in their approximation task. The resulting network called a `Recruiting Neural-Gas', organizes the neurons in the input space respecting the input data distribution and also the output error density. This algorithm gives very promising results and perspectives.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages91-96
Number of pages6
Volume3
Publication statusPublished - 2000
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'2000) - Como, Italy
Duration: 24 Jul 200027 Jul 2000

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'2000)
CityComo, Italy
Period24/7/0027/7/00

    Fingerprint

ASJC Scopus subject areas

  • Software

Cite this

Aupetit, M., Couturier, P., & Massotte, P. (2000). `Recruiting Neural-Gas' for function approximation. In Proceedings of the International Joint Conference on Neural Networks (Vol. 3, pp. 91-96). IEEE.