Estimating the Number of Components in a Mixture of Multilayer Perceptrons
| dc.creator | Olteanu, Madalina | |
| dc.creator | Rynkiewicz, Joseph | |
| dc.date | 2008-04-04 | |
| dc.date.accessioned | 2026-07-07T12:18:05Z | |
| dc.date.available | 2026-07-07T12:18:05Z | |
| dc.description | 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. | |
| dc.identifier | https://arxiv.org/abs/0804.0658 | |
| dc.identifier | http://arxiv.org/abs/0804.0658 | |
| dc.identifier | Neurocomputing / EEG Neurocomputing 71, 7-9 (2008) 1321-1329 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/212292 | |
| dc.subject | Statistics Theory | |
| dc.title | Estimating the Number of Components in a Mixture of Multilayer Perceptrons | |
| dc.type | text |