Abstract
Upper bounds on rates of approximation by neural networks are derived for functions representable as integrals in the form of networks with infinitely many units. The bounds are applied to perceptron networks.
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
Pisier, G.: Remarques sur un resultat non publié de B. Maurey. Seminaire d’Analyse Fonctionelle 1980-1981 I(12) (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 24, 608–613 (1992)
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transactions on Information Theory 39, 930–945 (1993)
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)
Kůrková: Minimization of error functionals over perceptron networks. Neural Computation 20(1), 252–270 (2008)
Kůrková, V., Sanguineti, M.: Error estimates for approximate optimization by the extended Ritz method. SIAM J. Optimization 2(15), 461–487 (2005)
Carroll, S.M., Dickinson, B.W.: Construction of neural nets using the Radon transform. In: Proceedings of IJCNN, vol. I, pp. 607–611. IEEE Press, New York (1989)
Ito, Y.: Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Networks 4, 385–394 (1991)
Girosi, F., Anzellotti, G.: Rates of convergence for radial basis functions and neural networks. In: Mammone, R.J. (ed.) Artificial Neural Networks for Speech and Vision, London, pp. 97–113. Chapman and Hall, Boca Raton (1993)
Kůrková, V., Kainen, P.C., Kreinovich, V.: Estimates of the number of hidden units and variation with respect to half-spaces. Neural Networks 10, 1061–1068 (1997)
Kainen, P.C., Kůrková, V., Vogt, A.: An integral formula for Heaviside neural networks. Neural Network World 10, 313–320 (2002)
Kainen, P.C., Kůrková, V., Vogt, A.: Integral combinations of Heavisides. Mathematische Nachrichten (to appear, 2008)
Barron, A.R.: Neural net approximation. In: Proc. 7th Yale Workshop on Adaptive and Learning Systems, pp. 69–72. Yale University Press (1992)
Kůrková, V.: Dimension–independent rates of approximation by neural networks. In: Warwick, K., Kárný, M. (eds.) Computer–Intensive Methods in Control and Signal Processing: Curse of Dimensionality, pp. 261–270. Birkhauser, Boston (1997)
Darken, C., Donahue, M., Gurvits, L., Sontag, E.: Rate of approximation results motivated by robust neural network learning. In: Proceedings of the 6th Annual ACM Conference on Computational Learning Theory, pp. 303–309. ACM, New York (1993)
Aronszajn, N.: Theory of reproducing kernels. Transactions of AMS 68, 337–404 (1950)
Kainen, P.C., Kůrková, V., Vogt, A.: A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves. Journal of Approximation Theory 147, 1–10 (2007)
Kainen, P.C., Kůrková, V.: An integral upper bound for neural-network approximation. Neural Computation, Research Report V-1023, Institute of Computer Science, Prague (submitted, 2008), http://www.cs.cas.cz/research
Kainen, P.C.: On evaluation of Bochner integrals. Research Report GU-08-30-07
Adams, R.A., Fournier, J.J.F.: Sobolev Spaces. Academic Press, Amsterdam (2003)
Kainen, P.C., Kůrková, V., Sanguineti, M.: Estimates of approximation rates by Gaussian radial-basis functions. In: Beliczynski, B., Dzielinski, A., Iwanowski, M., Ribeiro, B. (eds.) ICANNGA 2007. LNCS, vol. 4432, pp. 11–18. Springer, Heidelberg (2007)
Zaanen, A.C.: An Introduction to the Theory of Integration. North Holland, Amsterdam (1961)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kainen, P.C., Kůrková, V. (2008). Estimates of Network Complexity and Integral Representations. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-87536-9_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87535-2
Online ISBN: 978-3-540-87536-9
eBook Packages: Computer ScienceComputer Science (R0)