inria-00000599, version 2
Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis
Fabrice Rossi 1, 2Brieuc Conan-Guez 1, 2
Neural Networks 18, 1 (2005) 45--60
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.
- 1 : AxIS (INRIA Rocquencourt / INRIA Sophia Antipolis)
- INRIA
- 2 : CEntre de REcherches en MAthématiques de la DEcision (CEREMADE)
- CNRS : UMR7534 – Université Paris IX - Paris Dauphine
- Domaine : Informatique/Réseau de neurones
- Mots-clés : Functional data analysis – Multi-Layer Perceptron – Universal Approximation – Supervised learning – Curves discrimination – Learning consistancy – Nonlinear functional model – Spectrometric data
- Commentaire : http://www.sciencedirect.com/science/journal/08936080
- Versions disponibles : v1 (04-11-2005) v2 (23-09-2007)
- inria-00000599, version 2
- http://hal.inria.fr/inria-00000599
- oai:hal.inria.fr:inria-00000599
- Contributeur : Fabrice Rossi
- Soumis le : Dimanche 23 Septembre 2007, 15:02:49
- Dernière modification le : Dimanche 23 Septembre 2007, 16:10:58
Documents associés
Exporter