Estimation consistante de l'architecture des perceptrons multicouches

Details Estimation consistante de l'architecture des perceptrons multicouches Estimation consistante de l'architecture des perceptrons multicouches

2008-02-21

arxiv.org/abs/0802.3191v1

Comptes Rendus de l Acad\'emie des Sciences - Series I - Mathematics 342 (2006) 697-700

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 because the information matrix of Fisher is not invertible if this number is overestimated. However, if the parameters of the MLP are in a compact set, we prove that the minimization of a suitable information criteria leads to consistent estimation of the true number of hidden units.

Affiliated with

Also associated with

No associations

Rating

Estimation consistante de l'architecture des perceptrons multicouches 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 Estimation consistante de l'architecture des perceptrons multicouches, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Estimation consistante de l'architecture des perceptrons multicouches will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-580441