Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis - Archive ouverte HAL Access content directly
Journal Articles Neural Networks Year : 2005

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.
Fichier principal
Vignette du fichier
fmlp-neural-networks-preprint.pdf (372.09 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

Cite

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

Altmetric

Share

Gmail Facebook Twitter LinkedIn More