Springer
Table of ContentsAuthor IndexSearch

A New Method of Multilayer Perceptron Encoding

Emmanuel Blindauer and Jerzy Korczak

Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection,
UMR7005, CNRS,
67400 Illkirch, France.
{blindauer,jjk}@lsiit.u-strasbg.fr

Abstract. One of the central issues in neural network research is how to find an optimal MultiLayer Perceptron architecture. The number of neurons, their organization in layers, as well as their connection scheme have a considerable influence on network learning, and on the capacity for generalization [7]. A solution to find out these parameters is needed: The neuro-evolution ([1, 2, 4, 5]).

LNCS 2723, p. 369 f.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003