Abstract
Limitations of capabilities of shallow networks to represent sparsely real-valued functions on finite domains is investigated. Influence of sizes of function domains and of sizes dictionaries of computational units on sparsity of networks computing finite mappings is explored. It is shown that when dictionary is not sufficiently large with respect to the size of the finite domain, then almost any uniformly randomly chosen function on the domain either cannot be sparsely represented or its computation is unstable.
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 subscriptionsReferences
Ito, Y.: Finite mapping by neural networks and truth functions. Math. Sci. 17, 69–77 (1992)
Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numerica 8, 143–195 (1999)
Fine, T.L.: Feedforward Neural Network Methodology. Springer, Heidelberg (1999)
Bengio, Y., LeCun, Y.: Scaling learning algorithms towards AI. In: Bottou, L., Chapelle, O., DeCoste, D., Weston, J. (eds.) Large-Scale Kernel Machines. MIT Press (2007)
Ba, L.J., Caruana, R.: Do deep networks really need to be deep? In: Ghahrani, Z., et al. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 1–9 (2014)
Kainen, P.C., Kůrková, V., Sanguineti, M.: Dependence of computational models on input dimension: tractability of approximation and optimization tasks. IEEE Trans. Inf. Theory 58, 1203–1214 (2012)
Maiorov, V.E., Pinkus, A.: Lower bounds for approximation by MLP neural networks. Neurocomputing 25, 81–91 (1999)
Maiorov, V.E., Meir, R.: On the near optimality of the stochastic approximation of smooth functions by neural networks. Adv. Comput. Math. 13, 79–103 (2000)
Bengio, Y., Delalleau, O., Roux, N.L.: The curse of highly variable functions for local kernel machines. In: Advances in Neural Information Processing Systems, vol. 18, pp. 107–114. MIT Press (2006)
Bianchini, M., Scarselli, F.: On the complexity of neural network classifiers: a comparison between shallow and deep architectures. IEEE Trans. Neural Netw. Learn. Syst. 25, 1553–1565 (2014)
Kůrková, V., Sanguineti, M.: Model complexities of shallow networks representing highly varying functions. Neurocomputing 171, 598–604 (2016)
Kůrková, V.: Lower bounds on complexity of shallow perceptron networks. In: Jayne, C., Iliadis, L. (eds.) EANN 2016. CCIS, vol. 629, pp. 283–294. Springer, Heidelberg (2016)
Kůrková, V.: Constructive lower bounds on model complexity of shallow perceptron networks. Neural Comput. Appl. (2017). doi:10.1007/s00521-017-2965-0
Kůrková, V., Sanguineti, M.: Approximate minimization of the regularized expected error over kernel models. Math. Oper. Res. 33, 747–756 (2008)
Barron, A.R.: Neural net approximation. In: Narendra, K.S. (ed.) Proceedings of the 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)
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inf. Theory 39, 930–945 (1993)
Kůrková, V.: Complexity estimates based on integral transforms induced by computational units. Neural Netw. 33, 160–167 (2012)
Kůrková, V., Savický, P., Hlaváčková, K.: Representations and rates of approximation of real-valued Boolean functions by neural networks. Neural Netw. 11, 651–659 (1998)
Ball, K.: An elementary introduction to modern convex geometry. In: Levy, S. (ed.) Flavors of Geometry, pp. 1–58. Cambridge University Press (1997)
Matoušek, J.: Lectures on Discrete Geometry. Springer, New York (2002)
Schläfli, L.: Theorie der Vielfachen Kontinuität. Zürcher & Furrer, Zürich (1901)
Cover, T.M.: Geometrical and statistical properties of systems of linear inequalities with applictions in pattern recognition. IEEE Trans. Electron. Comput. 14, 326–334 (1965)
Candès, E.J.: The restricted isometric property and its implications for compressed sensing. C. R. Acad. Sci. Paris I 346, 589–592 (2008)
Roychowdhury, V., Siu, K.Y., Orlitsky, A.: Neural models and spectral methods. In: Roychowdhury, V., Siu, K., Orlitsky, A. (eds.) Theoretical Advances in Neural Computation and Learning, pp. 3–36. Springer, New York (1994)
Laughlin, S.B., Sejnowski, T.J.: Communication in neural networks. Science 301, 1870–1874 (2003)
Acknowledgments
This work was partially supported by the Czech Grant Agency grant 15-18108S and 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
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Kůrková, V. (2017). Sparsity of Shallow Networks Representing Finite Mappings. In: Boracchi, G., Iliadis, L., Jayne, C., Likas, A. (eds) Engineering Applications of Neural Networks. EANN 2017. Communications in Computer and Information Science, vol 744. Springer, Cham. https://doi.org/10.1007/978-3-319-65172-9_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-65172-9_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65171-2
Online ISBN: 978-3-319-65172-9
eBook Packages: Computer ScienceComputer Science (R0)