Estimating the Number of Components in a Mixture of Multilayer Perceptrons

Details Estimating the Number of Components in a Mixture of Multilayer Perceptrons Estimating the Number of Components in a Mixture of Multilayer Perceptrons

2008-04-04

arxiv.org/abs/0804.0658v1

Neurocomputing / EEG Neurocomputing 71, 7-9 (2008) 1321-1329

Mathematics

Statistics Theory

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Estimating the Number of Components in a Mixture of Multilayer Perceptrons does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Estimating the Number of Components in a Mixture of Multilayer Perceptrons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Estimating the Number of Components in a Mixture of Multilayer Perceptrons will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-190594