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.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Amari, S., Park, H., Ozeki, T.: Singularities Affect Dynamics of Learning in Neuromanifolds. Neural computation 18, 1007–1065 (2006)
Cottrell, M., Girard, B., Girard, Y., Mangeas, M., Muller, C.: Neural Modeling for Time Series: a Statistical Stepwise Method for Weight Elimination. IEEE Transaction on Neural Networks 6, 1355–1364 (1995)
Dacunha-Castelle, D., Gassiat, E.: Testing the Order of a Model Using Locally Conic Parameterization: Population Mixtures and Stationary ARMA process. The Annals of Statistics 27, 1178–1209 (1999)
Fukumizu, K.: A Regularity Condition of the Information Matrix of a Multilayer Perceptron Network. Neural networks 9, 871–879 (1996)
Fukumizu, K.: Likelihood Ratio of Unidentifiable Models and Multilayer Neural Networks. The Annals of Statistics 31, 833–851 (2003)
Gassiat, E., Keribin, C.: The Likelihood Ratio Test for the Number of Components in a Mixture with Markov Regime. ESAIM Probability and statistics 4, 25–52 (2000)
Gassiat, E.: Likelihood Ratio Inequalities with Applications to Various Mixtures. Annales de l’Institut Henri Poincaré 38, 897–906 (2002)
Mangeas, M.: Neural Model Selection: How to Determine the Fittest Criterion. In: Gerstner, W., Hasler, M., Germond, A., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 987–992. Springer, Heidelberg (1997)
Liu, X., Shao, Y.: Asymptotics for Likelihood Ratio Tests Under Loss of Identifiability. The Annals of Statistics 31, 807–832 (2003)
Sussmann, H.J.: Uniqueness of the Weights for Minimal Feed-Forward Nets with a Given Input-Output Map. Neural networks 5, 589–593 (1992)
Van der Vaart, A.W.: Asymptotic Statistics. Cambridge University Press, Cambridge (1998)
White, H.: Artificial Neural Networks: Approximation and Learning Theory. Oxford, Basil Blackwell (1992)
Yao, J.: On Least Square Estimation for Stable Nonlinear AR Processes. The Annals of Institut. of Mathematical Statistics 52, 316–331 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rynkiewicz, J. (2008). Asymptotic Law of Likelihood Ratio for Multilayer Perceptron Models. In: Sun, F., Zhang, J., Tan, Y., Cao, J., Yu, W. (eds) Advances in Neural Networks - ISNN 2008. ISNN 2008. Lecture Notes in Computer Science, vol 5263. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87732-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-540-87732-5_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87731-8
Online ISBN: 978-3-540-87732-5
eBook Packages: Computer ScienceComputer Science (R0)