Asymptotic law of likelihood ratio for multilayer perceptron models

Details Asymptotic law of likelihood ratio for multilayer perceptron models Asymptotic law of likelihood ratio for multilayer perceptron models

2010-11-28

arxiv.org/abs/1011.6039v1

Mathematics

Statistics Theory

19 pages

Scientific paper

We consider regression models involving multilayer perceptrons (MLP) with one hidden layer and a Gaussian noise. The data are assumed to be generated by a true MLP model and the estimation of the parameters of the MLP is done by maximizing the likelihood of the model. When the number of hidden units of the true model is known, the asymptotic distribution of the maximum likelihood estimator (MLE) and the likelihood ratio (LR) statistic is easy to compute and converge to a $\chi^2$ law. However, if the number of hidden unit is over-estimated the Fischer information matrix of the model is singular and the asymptotic behavior of the MLE is unknown. This paper deals with this case, and gives the exact asymptotic law of the LR statistics. Namely, if the parameters of the MLP lie in a suitable compact set, we show that the LR statistics is the supremum of the square of a Gaussian process indexed by a class of limit score functions.

Affiliated with

Also associated with

No associations

Rating

Asymptotic law of likelihood ratio for multilayer perceptron models 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 Asymptotic law of likelihood ratio for multilayer perceptron models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Asymptotic law of likelihood ratio for multilayer perceptron models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-321592