Abstract
Model complexity of feedforward neural networks is studied in terms of rates of variable-basis approximation. Sets of functions, for which the errors in approximation by neural networks with n hidden units converge to zero geometrically fast with increasing number n, are described. However, the geometric speed of convergence depends on parameters, which are specific for each function to be approximated. The results are illustrated by examples of estimates of such parameters for functions in infinite-dimensional Hilbert spaces.
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
Pinkus, A.: N-widths in Approximation Theory. Springer, New York (1986)
Pisier, G.: Remarques sur un résultat non publié de B. Maurey. In: Séminaire d’Analyse Fonctionnelle, vol. I(12), École Polytechnique, Centre de Mathématiques, Palaiseau (1980–1981)
Jones, L.K.: A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Annals of Statistics 20, 608–613 (1992)
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. on Information Theory 39, 930–945 (1993)
Kůrková, V., Savický, P., Hlaváčková, K.: Representations and rates of approximation of real–valued Boolean functions by neural networks. Neural Networks 11, 651–659 (1998)
Kůrková, V., Sanguineti, M.: Bounds on rates of variable-basis and neural-network approximation. IEEE Trans. on Information Theory 47, 2659–2665 (2001)
Makovoz, Y.: Random approximants and neural networks. J. of Approximation Theory 85, 98–109 (1996)
Kůrková, V., Sanguineti, M.: Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets. Discrete Applied Mathematics 155, 1930–1942 (2007)
Lavretsky, E.: On the geometric convergence of neural approximations. IEEE Trans. on Neural Networks 13, 274–282 (2002)
Kůrková, V.: Dimension-independent rates of approximation by neural networks. In Warwick, K., Kárný, M. (eds.) Computer-Intensive Methods in Control and Signal Processing. The Curse of Dimensionality. Birkhäuser, Boston, pp. 261–270 (1997)
Kůrková, V.: High-dimensional approximation and optimization by neural networks. In: Suykens, J., Horváth, G., Basu, S., Micchelli, C., Vandewalle, J. (eds.) Advances in Learning Theory: Methods, Models and Applications, Ch. 4., pp. 69–88. IOS Press, Amsterdam (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kůrková, V., Sanguineti, M. (2008). Geometric Rates of Approximation by Neural Networks. In: Geffert, V., Karhumäki, J., Bertoni, A., Preneel, B., Návrat, P., Bieliková, M. (eds) SOFSEM 2008: Theory and Practice of Computer Science. SOFSEM 2008. Lecture Notes in Computer Science, vol 4910. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77566-9_47
Download citation
DOI: https://doi.org/10.1007/978-3-540-77566-9_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77565-2
Online ISBN: 978-3-540-77566-9
eBook Packages: Computer ScienceComputer Science (R0)