Estimating the Number of Components in a Mixture of Multilayer Perceptrons

dc.creatorOlteanu, Madalina
dc.creatorRynkiewicz, Joseph
dc.date2008-04-04
dc.date.accessioned2026-07-07T12:18:05Z
dc.date.available2026-07-07T12:18:05Z
dc.descriptionBIC 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.
dc.identifierhttps://arxiv.org/abs/0804.0658
dc.identifierhttp://arxiv.org/abs/0804.0658
dc.identifierNeurocomputing / EEG Neurocomputing 71, 7-9 (2008) 1321-1329
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/212292
dc.subjectStatistics Theory
dc.titleEstimating the Number of Components in a Mixture of Multilayer Perceptrons
dc.typetext

Files

Collections