Numéro
J. Phys. IV France
Volume 12, Numéro 1, mars 2002
Page(s) 157 - 188
DOI https://doi.org/10.1051/jp42002007




J. Phys. IV France
12 (2002) Pr1-157
DOI: 10.1051/jp42002007

Les perceptrons multicouches : de la régression non-linéaire aux problèmes inverses

F. Badran and S. Thiria

Laboratoire d'Océanographie Dynamique et Climatologie, 4 place Jussieu, 75005 Paris, France CÉDRIC, Conservatoire National des Arts et Métiers, 292 rue Saint-Martin, 75003 Paris, France

Abstract
The problem of nonlinear least square regression using multi-layered perceptrons is addressed in this paper. A general formulation using maximum likelihood is given and a particular attention is paid to algorithm accounting for uncertainties. The generalization to density estimation is given. In the second part of the paper, a general framework allows to modelize general inverse problems.


PDF File (2.27 MB)
Contents

© EDP Sciences 2002