Abstract
Approximation of solutions of integral equations by networks with kernel units is investigated theoretically. There are derived upper bounds on speed of decrease of errors in approximation of solutions of Fredholm integral equations by kernel networks with increasing numbers of units. The estimates are obtained for Gaussian and degenerate kernels.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Lovitt, W.V.: Linear Integral Equations. Dover, New York (1950)
Lonseth, A.T.: Sources and applications of integral equations. SIAM Review 19, 241–278 (1977)
Effati, S., Buzhabadi, R.: A neural network approach for solving Fredholm integral equations of the second kind. Neural Computing & and Applications (2010), doi:10.1007/s00521–010–0489–y
Alipanah, A., Esmaeili, S.: Numerical solution of the two-dimensional Fredholm integral equations by Gaussian radial basis function. J. of Comput. and Appl. Math (2009), doi:doi:10.1016/j.cam.2009.11.053
Golbabai, A., Seifollahi, S.: Numerical solution of the second kind integral equations using radial basis function networks. Appl. Math. and Comput. 174, 877–883 (2006)
Kůrková, V., Sanguineti, M.: Geometric upper bounds on rates of variable-basis approximation. IEEE Trans. on Inf. Th. 54, 5681–5688 (2008)
Gnecco, G., Kůrková, V., Sanguineti, M.: Some comparisons of complexity in dictionary-based and linear computational models. Neural Networks 24, 171–182 (2011)
Alessandri, A., Sanguineti, M.: Optimization of approximating networks for optimal fault diagnosis. Optim. Meth. and Soft. 20, 235–260 (2005)
Giulini, S., Sanguineti, M.: Approximation schemes for functional optimization problems. J. of Optim. Th. and Appl. 140, 33–54 (2009)
Gnecco, G., Sanguineti, M.: Accuracy of suboptimal solutions to kernel principal component analysis. Comput. Optim. and Appl. 42, 265–287 (2009)
Kainen, P.C., Kůrková, V., Sanguineti, M.: Complexity of Gaussian radial-basis networks approximating smooth functions. J. of Complexity 25, 63–74 (2009)
Kůrková, V., Sanguineti, M.: Approximate minimization of the regularized expected error over kernel models. Math. of Op. Res. 33, 747–756 (2008)
Gribonval, R., Vandergheynst, P.: On the exponential convergence of matching pursuits in quasi-incoherent dictionaries. IEEE Trans. on Inf. Th. 52, 255–261 (2006)
Jones, L.K.: A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Ann. of Stat. 20, 608–613 (1992)
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. on Inf. Th. 39, 930–945 (1993)
Darken, C., Donahue, M., Gurvits, L., Sontag, E.: Rate of approximation results motivated by robust neural network learning. In: Proc. 6th Annual ACM Conf. on Computational Learning Theory, pp. 303–309 (1993)
Girosi, F.: Approximation error bounds that use VC- bounds. In: Proc. Int. Conf. on Artificial Neural Networks, pp. 295–302 (1995)
Gurvits, L., Koiran, P.: Approximation and learning of convex superpositions. J. of Computer and System Sciences 55, 161–170 (1997)
Vapnik, V.N.: Statistical Learning Theory. Wiley, New York (1998)
Atkinson, K.: The Numerical Solution of Integral Equations of the Second Kind. Cambridge Univ. Press, Cambridge (1997)
Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numerica 8, 143–195 (1999)
Park, J., Sandberg, I.W.: 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)
Dudley, R.M.: Balls in \(\mathcal{R}^k\) do not cut all subsets of k+2 points. Advances in Math. 31, 306–308 (1979)
Tricomi, F.G.: Integral Equations. Interscience, New York (1957)
Sontag, E.: VC dimension of neural networks. In: Bishop, C. (ed.) Neural Networks and Machine Learning, pp. 69–95. Springer, Berlin (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gnecco, G., Kůrková, V., Sanguineti, M. (2011). Bounds for Approximate Solutions of Fredholm Integral Equations Using Kernel Networks. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2011. ICANN 2011. Lecture Notes in Computer Science, vol 6791. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21735-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-21735-7_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21734-0
Online ISBN: 978-3-642-21735-7
eBook Packages: Computer ScienceComputer Science (R0)