Estimating the Number of Components in a Mixture of Multilayer Perceptrons - Archive ouverte HAL
Article Dans Une Revue Neurocomputing Année : 2008

Estimating the Number of Components in a Mixture of Multilayer Perceptrons

Résumé

BIC criterion is widely used by the neural-network community for model selection tasks, although its convergence properties are not always theoretically established. In this paper we will focus on estimating the number of components in a mixture of multilayer perceptrons and proving the convergence of the BIC criterion in this frame. The penalized marginal-likelihood for mixture models and hidden Markov models introduced by Keribin (2000) and, respectively, Gassiat (2002) is extended to mixtures of multilayer perceptrons for which a penalized-likelihood criterion is proposed. We prove its convergence under some hypothesis which involve essentially the bracketing entropy of the generalized score-functions class and illustrate it by some numerical examples.
Fichier principal
Vignette du fichier
neurocomputing.pdf (238.62 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00270181 , version 1 (04-04-2008)

Identifiants

Citer

Madalina Olteanu, Joseph Rynkiewicz. Estimating the Number of Components in a Mixture of Multilayer Perceptrons. Neurocomputing, 2008, 71 (7-9), pp.1321-1329. ⟨10.1016/j.neucom.2007.12.022⟩. ⟨hal-00270181⟩
99 Consultations
115 Téléchargements

Altmetric

Partager

More