Genetic Extensions of Neural Net Learning: Transfer Functions and Renormalisation Coefficients - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 1994

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

Abstract

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
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-02985496 , version 1

Cite

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 View
14 Download

Share

Gmail Facebook X LinkedIn More