Abstract
Model complexities of networks representing multivariable functions is studied in terms of variational norms tailored to types of network units. It is shown that the size of the variational norm reflects both the number of hidden units and sizes of output weights. Lower bounds on growth of variational norms with increasing input dimension d are derived for Gaussian units and perceptrons. It is proven that variation of the d-dimensional parity with respect to Gaussian Support Vector Machines grows exponentially with d and for large values of d, almost any randomly-chosen Boolean function has variation with respect to perceptrons depending on d exponentially.
This is a preview of subscription content, log in via an institution to check access.
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
Bengio, Y.: Learning deep architectures for AI. Foundations and Trends in Machine Learning 2, 1–127 (2009)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18, 1527–1554 (2006)
Chow, T.W.S., Cho, S.Y.: Neural Networks and Computing: Learning Algorithms and Applications. World Scientific (2007)
Leshno, M., Lin, V.Y., Pinkus, A., Schocken, S.: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks 6, 861–867 (1993)
Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numerica 8, 143–195 (1999)
Park, J., Sandberg, I.: Approximation and radial-basis-function networks. Neural Computation 5, 305–316 (1993)
Mhaskar, H.N.: Versatile Gaussian networks. In: Proc. of IEEE Workshop of Nonlinear Image Processing, pp. 70–73 (1995)
Kůrková, V.: Some comparisons of networks with radial and kernel units. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part II. LNCS, vol. 7553, pp. 17–24. Springer, Heidelberg (2012)
Kainen, P.C., Kůrková, V., Sanguineti, M.: Dependence of computational models on input dimension: Tractability of approximation and optimization tasks. IEEE Transactions on Information Theory 58, 1203–1214 (2012)
Maiorov, V.: On best approximation by ridge functions. J. of Approximation Theory 99, 68–94 (1999)
Maiorov, V., Pinkus, A.: Lower bounds for approximation by MLP neural networks. Neurocomputing 25, 81–91 (1999)
Bartlett, P.L.: The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network. IEEE Trans. on Information Theory 44, 525–536 (1998)
Bengio, Y., Delalleau, O., Roux, N.L.: The curse of highly variable functions for local kernel machines. In: Advances in Neural Information Processing Systems 18, pp. 107–114. MIT Press (2006)
Ito, Y.: Finite mapping by neural networks and truth functions. Mathematical Scientist 17, 69–77 (1992)
Micchelli, C.A.: Interpolation of scattered data: Distance matrices and conditionally positive definite functions. Constructive Approximation 2, 11–22 (1986)
Barron, A.R.: Neural net approximation. In: Narendra, K. (ed.) 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. The Curse of Dimensionality, pp. 261–270. Birkhäuser, Boston (1997)
Kůrková, V., Sanguineti, M.: Comparison of worst-case errors in linear and neural network approximation. IEEE Transactions on Information Theory 48, 264–275 (2002)
Gnecco, G., Sanguineti, M.: On a variational norm tailored to variable-basis approximation schemes. IEEE Trans. on Information Theory 57, 549–558 (2011)
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.: Complexity estimates based on integral transforms induced by computational units. Neural Networks 33, 160–167 (2012)
Schläfli, L.: Theorie der vielfachen Kontinuität. Zürcher & Furrer, Zürich (1901)
Roychowdhury, V., Siu, K., Orlitsky, A.: Neural models and spectral methods. In: Roychowdhury, V., Siu, K., Orlitsky, A. (eds.) Theorertical Advances in Neural Computation and Learning, pp. 3–36. Kluwer Academic Publishers (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kůrková, V., Sanguineti, M. (2014). Complexity of Shallow Networks Representing Functions with Large Variations. In: Wermter, S., et al. Artificial Neural Networks and Machine Learning – ICANN 2014. ICANN 2014. Lecture Notes in Computer Science, vol 8681. Springer, Cham. https://doi.org/10.1007/978-3-319-11179-7_42
Download citation
DOI: https://doi.org/10.1007/978-3-319-11179-7_42
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11178-0
Online ISBN: 978-3-319-11179-7
eBook Packages: Computer ScienceComputer Science (R0)