Abstract
Distributions of errors in approximation of binary-valued functions by networks with sets of input-output functions of finite VC dimension is investigated. Conditions on concentration of approximation errors around their mean values are derived in terms of growth functions of sets of input-output functions. Limitations of approximation capabilities of networks of finite VC dimension are discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kainen, P.C., Kůrková, V., Sanguineti, M.: Dependence of computational models on input dimension: tractability of approximation and optimization tasks. IEEE Trans. Inf. Theor. 58, 1203–1214 (2012)
Telgarsky, M.: Benefits of depth in neural networks. Proc. Mach. Learn. Res. 49, 1517–1539 (2016)
Yarotsky, D.: Error bounds for approximations with deep ReLU networks. Neural Netw. 94, 103–114 (2017)
Gorban, A., Tyukin, I., Prokhorov, D., Sofeikov, K.: Approximation with random bases: pro et contra. Inf. Sci. 364–365, 129–145 (2016)
Gorban, A., Tyukin, I.: Blessing of dimensionality: mathematical foundations of the statistical physics of data. Philos. Trans. Royal Soc. A 376, 2017–2037 (2018)
Gorban, A.N., Makarov, V.A., Tyukin, I.Y.: The unreasonable effectiveness of small neural ensembles in high-dimensional brain. Phys. Life Rev. 29, 55–88 (2019)
Kůrková, V., Sanguineti, M.: Model complexities of shallow networks representing highly varying functions. Neurocomputing 171, 598–604 (2016)
Kůrková, V., Sanguineti, M.: Probabilistic lower bounds for approximation by shallow perceptron networks. Neural Netw. 91, 34–41 (2017)
Kůrková, V.: Some insights from high-dimensional spheres. Phys. Life Rev. 29, 98–100 (2019)
Lévy, P., Pellegrino, F.: Problémes concrets d’analyse fonctionnelle. Gauthier-Villars, Paris (1951)
Milman, V., Schechtman, G.: Asymptotic theory of finite dimensional normed spaces. Volume 1200 of Lecture Notes in Mathematics. Springer-Verlag (1986)
Chernoff, H.: A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Ann. Math. Stat. 23, 493–507 (1952)
Hoeffding, W.: Probability inequalities for sums of bounded random variables. J. Am. Stat. Assoc. 58, 13–30 (1963)
Vershynin, R.: High-Dimensional Probability. University of California, Irvine (2020)
McDiarmid, C.: On the method of bounded differences. In: Siemons, J. (ed.) Surveys in Combinatorics, pp. 148–188. Cambridge University Press, Cambridge (1989)
Vapnik, V.N., Chervonenkis, A.Y.: On the uniform convergence of relative frequencies of events to their probabilities. Dokl. Akad. Nauk SSSR 16(2), 264–279 (1971)
Dubhashi, D., Panconesi, A.: Concentration of Measure for the Analysis of Randomized Algorithms. Cambridge University Press (2009)
Shelah, S.: A combinatorial problem; stability and order for models and theories in infinitary languages. Pac. J. Math. 41, 247–261 (1972)
Sauer, N.: On the density of families of sets. J. Comb. Theor. 13, 145–147 (1972)
Kůrková, V., Sanguineti, M.: Correlations of random classifiers on large data sets. Soft. Comput. 25(19), 12641–12648 (2021). https://doi.org/10.1007/s00500-021-05938-4
Kůrková, V., Sanguineti, M.: Approximation of classifiers by deep perceptron networks. Neural Netw. 165, 654–661 (2023)
Acknowledgments
This work was partially supported by the Czech Science Foundation grant 22-02067S and the institutional support of the Institute of Computer Science RVO 67985807.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kůrková, V. (2023). Approximation of Binary-Valued Functions by Networks of Finite VC Dimension. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14254. Springer, Cham. https://doi.org/10.1007/978-3-031-44207-0_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-44207-0_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44206-3
Online ISBN: 978-3-031-44207-0
eBook Packages: Computer ScienceComputer Science (R0)