Genetic Extensions of Neural Net Learning: Transfer Functions and Renormalisation Coefficients - Département de mathématiques appliquées Accéder directement au contenu
Communication Dans Un Congrès Année : 1994

Genetic Extensions of Neural Net Learning: Transfer Functions and Renormalisation Coefficients

Résumé

This paper deals with technical issues relevant to artificial neural net (ANN) training by genetic algorithms. Neural nets have applications ranging from perception to control; in the context of control, achieving great precision is more critical than in pattern recognition or classification tasks. In previous work, the authors have found that when employing genetic search to train a net, both precision and training speed can be greatly enhanced by an input renormalisation technique. In this paper we investigate the automatic tuning of such renormalisation coefficients, as well as the tuning of the slopes of the transfer functions of the individual neurons in the net. Waiting time analysis is presented as an alternative to the classical "mean perfomance" interpretation of GA experiments. It is felt that it provides a more realistic evaluation of the real-world usefulness of a GA.
Fichier principal
Vignette du fichier
ronaldSchoenauerEA94.pdf (263.45 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02985496 , version 1 (02-11-2020)

Identifiants

  • HAL Id : hal-02985496 , version 1

Citer

Marc Schoenauer, Edmund Ronald. Genetic Extensions of Neural Net Learning: Transfer Functions and Renormalisation Coefficients. Proc. EA94, the first Evolution Artificielle conference, Sep 1994, Toulouse, France. ⟨hal-02985496⟩
31 Consultations
15 Téléchargements

Partager

Gmail Facebook X LinkedIn More