nach oben

Erschienen in:

2014 | OriginalPaper | Buchkapitel

Accuracy of Surrogate Solutions of Integral Equations by Feedforward Networks

verfasst von : Věra Kůrková

Erschienen in: Issues and Challenges of Intelligent Systems and Computational Intelligence

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Surrogate solutions of Fredholm integral equations by feedforward neural networks are investigated theoretically. Convergence of surrogate solutions computable by networks with increasing numbers of computational units to theoretically optimal solutions is proven and upper bounds on rates of convergence are derived. The results hold for a variety of computational units, they are illustrated by examples of perceptrons and Gaussian radial units.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Construction Site Layout and Building Material Distribution Planning Using Hybrid Algorithms

Nächstes Kapitel Vehicle Classification Using Neural Networks with a Single Magnetic Detector

Forrester, A., Sobester, A., Keane, A.: Engineering Design via Surrogate Modelling: A Practical Guide. Wiley, Chichester (2008)CrossRef

Baerns, M., Holeňa, M.: Combinatorial Development of Solid Catalytic Materials. Imperial College Press, London (2009)

Park, J., Sandberg, I.W.: Approximation and radial-basis-function networks. Neural Comput. 5, 305–316 (1993)CrossRef

Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numerica 8, 143–195 (1999)CrossRefMathSciNet

Kainen, P.C., K\(\mathring{\rm u}\)rková, V., Sanguineti, M.: Dependence of computational models on input dimension: Tractability of approximation and optimization tasks. IEEE Trans. Inf. Theory 58(2), 1203–1214 (2012)

Lovitt, W.V.: Linear Integral Equations. Dover, New York (1950)

Lonseth, A.T.: Sources and applications of integral equations. SIAM Rev. 19, 241–278 (1977)CrossRefMATHMathSciNet

Lu, Y., Shen, L., Xu, Y.: Integral equation models for image restoration: high accuracy methods and fast algorithms. Inverse Prob. 26, 045006 (2010)CrossRefMathSciNet

Steinwart, I., Christmann, A.: Support Vector Machines. Springer, New York (2008)MATH

10.

Golbabai, A., Seifollahi, S.: Numerical solution of the second kind integral equations using radial basis function networks. Appl. Math. Comput. 174, 877–883 (2006)CrossRefMATHMathSciNet

11.

Effati, S., Buzhabadi, R.: A neural network approach for solving Fredholm integral equations of the second kind. Neural Comput. Appl. 21(5), 843–852 (2012)CrossRef

12.

Gnecco, G., K\(\mathring{\rm u}\)rková, V., Sanguineti, M.: Bounds for approximate solutions of Fredholm integral equations using kernel networks. In: Honkela, T., et al. (eds.) Lecture Notes in Computer Science (Proceedings of ICANN 2011), vol. 6791, pp. 126–133. Springer, Heidelberg (2011)

13.

Gnecco, G., K\(\mathring{\rm u}\)rková, V., Sanguineti, M.: Accuracy of approximations of solutions to Fredholm equations by kernel methods. Appl. Math. Comput. 218, 7481–7497 (2012)

14.

K\(\mathring{\rm u}\)rková, V.: Surrogate modeling of solutions of integral equations by neural networks. In: Iliadis, L., et al., (eds.), AIAI 2012—Artificial Intelligence Applications and Innovations, IFIP AICT 381, IFIP International Federation for Information Processing (2012), pp. 88-96

15.

Gnecco, G., K\(\mathring{\rm u}\)rková, V., Sanguineti, M.: Some comparisons of complexity in dictionary-based and linear computational models. Neural Netw. 24, 171–182 (2011)

16.

Gnecco, G., K\(\mathring{\rm u}\)rková, V., Sanguineti, M.: Can dictionary-based computational models outperform the best linear ones? Neural Netw. 24, 881–887 (2011)

17.

Gribonval, R., Vandergheynst, P.: On the exponential convergence of matching pursuits in quasi-incoherent dictionaries. IEEE Trans. Inf. Theory 52, 255–261 (2006)CrossRefMathSciNet

18.

Rudin, W.: Functional Analysis. McGraw-Hill, Boston (1991)MATH

19.

Atkinson, K.: The Numerical Solution of Integral Equations of the Second Kind. Cambridge University Press, Cambridge (1997)CrossRefMATH

20.

Courant, R., Hilbert, D.: Methods of Mathematical Physics, vol. I. Wiley, New York (1989)CrossRef

21.

Barron, A.R.: Neural net approximation. In: Narendra, K. (ed.) Proceedings of 7th Yale Workshop on Adaptive and Learning Systems. Yale University Press, New Haven (1992)

22.

K\(\mathring{\rm u}\)rková, 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)

23.

K\(\mathring{\rm u}\)rková, 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 (Chapter 4), pp. 69–88. IOS Press, Amsterdam (2003)

24.

Kainen, P.C., K\(\mathring{\rm u}\)rková, V., Sanguineti, M.: Complexity of Gaussian radial-basis networks approximating smooth functions. J. Complexity 25, 63–74 (2009)

25.

Pisier, G.: Remarques sur un résultat non publié de B. Maurey. In: Séminaire d’Analyse Fonctionnelle 1980–1981, vol. I, no. 12, École Polytechnique, Centre de Mathématiques, Palaiseau, France (1981)

26.

Jones, L.K.: A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Ann. Stat. 20, 608–613 (1992)CrossRefMATH

27.

Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inf. Theory 39, 930–945 (1993)CrossRefMATHMathSciNet

28.

K\(\mathring{\rm u}\)rková, V.: Complexity estimates based on integral transforms induced by computational units. Neural Netw. 30, 160–167 (2012)

29.

K\(\mathring{\rm u}\)rková, V., Sanguineti, M.: Bounds on rates of variable-basis and neural-network approximation. IEEE Trans. Inf. Theory 47, 2659–2665 (2001)

30.

Kainen, P.C., K\(\mathring{\rm u}\)rková, V., Vogt, A.: A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves. J. Approx. Theory 147, 1–10 (2007)

Titel: Accuracy of Surrogate Solutions of Integral Equations by Feedforward Networks
verfasst von: Věra Kůrková
Verlag: Springer International Publishing
Buch: Issues and Challenges of Intelligent Systems and Computational Intelligence
Print ISBN: 978-3-319-03205-4

Electronic ISBN: 978-3-319-03206-1

Copyright-Jahr: 2014
DOI: https://doi.org/10.1007/978-3-319-03206-1_7

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"