Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Neural Networks Année : 2005

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

Résumé

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.
Fichier principal
Vignette du fichier
fmlp-neural-networks-preprint.pdf (380.1 Ko) Télécharger le fichier

Dates et versions

inria-00000599 , version 1 (04-11-2005)
inria-00000599 , version 2 (23-09-2007)

Identifiants

Citer

Fabrice Rossi, Brieuc Conan-Guez. Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis. Neural Networks, 2005, Neural Networks, 18 (1), pp.45--60. ⟨10.1016/j.neunet.2004.07.001⟩. ⟨inria-00000599v1⟩
212 Consultations
300 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More