Asymptotic Law of Likelihood Ratio for Multilayer Perceptron Models

Authors:
Joseph Rynkiewicz
Affiliations:
CES-SAMOS-MATISSE, Université de Paris 1, Paris 750013
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Year:
2008

Citing 6
Cited 0

Original Contribution: Uniqueness of the weights for minimal feedforward nets with a given input-output map

Neural Networks
A regularity condition of the information matrix of a multilayer perceptron network

Neural Networks
Artificial Neural Networks: Approximation and Learning Theory

Artificial Neural Networks: Approximation and Learning Theory
Neural Model Selection: How to Determine the Fittest Criterion?

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Singularities Affect Dynamics of Learning in Neuromanifolds

Neural Computation
Neural modeling for time series: A statistical stepwise method for weight elimination

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 model is over-estimated, the Fischer information matrix of the model is singular and the asymptotic behavior of the LR statistic is unknown or can be divergent if the set of possible parameter is too large. This paper deals with this case, and gives the exact asymptotic law of the LR statistic. Namely, if the parameters of the MLP lie in a suitable compact set, we show that the LR statistic converges to the maximum of the square of a Gaussian process indexed by a class of limit score functions.