Consistent estimation of the architecture of multilayer perceptrons

Details Consistent estimation of the architecture of multilayer perceptrons Consistent estimation of the architecture of multilayer perceptrons

2008-02-22

arxiv.org/abs/0802.3327v1

Dans ESANN 2006 - ESANN 2006, Bruges : Belgique (2006)

Mathematics

Statistics Theory

Scientific paper

We consider regression models involving multilayer perceptrons (MLP) with one hidden layer and a Gaussian noise. The estimation of the parameters of the MLP can be done by maximizing the likelihood of the model. In this framework, it is difficult to determine the true number of hidden units using an information criterion, like the Bayesian information criteria (BIC), because the information matrix of Fisher is not invertible if the number of hidden units is overestimated. Indeed, the classical theoretical justification of information criteria relies entirely on the invertibility of this matrix. However, using recent methodology introduced to deal with models with a loss of identifiability, we prove that suitable information criterion leads to consistent estimation of the true number of hidden units.

Affiliated with

Also associated with

No associations

Rating

Consistent estimation of the architecture 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 Consistent estimation of the architecture of multilayer perceptrons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Consistent estimation of the architecture of multilayer perceptrons will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-303355