Abstract
In this paper the large sample properties of neural networks estimators in a regression model with ϕ-mixing errors are investigated. In particular, using the theory of M-estimators, it is proved that the minimum squared error estimators of the connection weights and of the fitted values are consistent and asymptotically Normal.
The paper is partially supported by MURST ‘98 “Modelli statistici per l’analisi delle serie temporali”
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Barron, A.R. (1993) Universal Approximation Bounds for Superpositions of a Sigmoidal Function, IEEE Transactions on Information Theory, 39, No. 3, 930–945.
Billingsley, P. (1968) Convergence of Probability Measures, J. Wiley & Sons, New-York
Giordano, F. Perna, C. (1998) Proprietà asintotiche degli stimatori neurali nella regressione non parametrica, Atti della XXXIX Riunione Scientifica S.I.S.
Huber, P. (1981) Robust Statistics, J. Wiley & Sons, New-York.
Serfling, R. (1980) Approximation theorems of mathematical statistics, J. Wiley & Sons, New-York.
White, A. (1989) Some Asymptotic Results for Learning in Single Hidden-Layer Feedforward Network Models, Journal of the American Statistical Association, 84, No. 408, 1003–1013.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Giordano, F., Perna, C. (2001). Large-sample Properties of Neural Estimators in a Regression Model with ϕ-mixing Errors1 . In: Borra, S., Rocci, R., Vichi, M., Schader, M. (eds) Advances in Classification and Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-59471-7_35
Download citation
DOI: https://doi.org/10.1007/978-3-642-59471-7_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41488-9
Online ISBN: 978-3-642-59471-7
eBook Packages: Springer Book Archive