Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis

Abstract : In this paper, we study a natural extension of Multi-Layer Perceptrons (MLP) to functional inputs. We show that fundamental results for classical MLP can be extended to functional MLP. We obtain universal approximation results that show the expressive power of functional MLP is comparable to that of numerical MLP. We obtain consistency results which imply that the estimation of optimal parameters for functional MLP is statistically well defined. We finally show on simulated and real world data that the proposed model performs in a very satisfactory way.
Type de document :
Article dans une revue
Neural Networks, Elsevier, 2005, 18 (1), pp.45--60. <10.1016/j.neunet.2004.07.001>
Liste complète des métadonnées

https://hal.inria.fr/inria-00000599
Contributeur : Fabrice Rossi <>
Soumis le : dimanche 23 septembre 2007 - 15:02:49
Dernière modification le : mercredi 28 septembre 2016 - 16:02:09
Document(s) archivé(s) le : mardi 21 septembre 2010 - 13:49:29

Fichiers

fmlp-neural-networks-preprint....
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Fabrice Rossi, Brieuc Conan-Guez. Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis. Neural Networks, Elsevier, 2005, 18 (1), pp.45--60. <10.1016/j.neunet.2004.07.001>. <inria-00000599v2>

Partager

Métriques

Consultations de
la notice

306

Téléchargements du document

168