An Integral Upper Bound for Neural Network Approximation

Neural Computation

Volumn 21, Issue 10, 2009, Pages 2970-2989

  Kainen, Paul C ^a   Kůrková, Věra ^b  

^a GEORGETOWN UNIVERSITY   (United States)

^b INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION ERRORS; HIDDEN LAYER NETWORKS; HIDDEN UNITS; INTEGRAL REPRESENTATION; NEURAL-NETWORK APPROXIMATIONS; NONLINEAR APPROXIMATION; NONLINEAR INTEGRATION; PERCEPTRON NETWORK; UPPER BOUND;

NETWORK LAYERS;

ACTION POTENTIAL; ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BRAIN; COMPUTER SIMULATION; NERVE CELL; NERVE CELL NETWORK; PHYSIOLOGY;

ACTION POTENTIALS; ALGORITHMS; BRAIN; COMPUTER SIMULATION; NERVE NET; NEURAL NETWORKS (COMPUTER); NEURONS;

EID: 70350222271     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/neco.2009.04-08-745     Document Type: Letter

References (22)

1. Adams, R. A., & Fournier, J. J. F. (2003). Sobolev spaces. Orlando, FL: Academic Press.
2. Aronszajn, N. (1950). Theory of reproducing kernels. Transactions of AMS, 68, 337– 404.
3. Barron, A. R. (1992). Neural net approximation. In Proc. 7th Yale Workshop on Adaptive and Learning Systems (pp. 69–72). New Haven, CT: Yale University Press.
4. Barron, A. R. (1993). Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transactions on Information Theory, 39, 930–945.
5. Darken, C., Donahue, M., Gurvits, L., & Sontag, E. (1993). Rate of approximation results motivated by robust neural network learning. In Proceedings of the 6th Annual ACM Conference on Computational Learning Theory (pp. 303–309). New York: ACM.
6. Donahue, M., Gurvits, L., Darken, C., & Sontag, E. (1997). Rates of convex approximation in non-Hilbert spaces. Constructive Approximation, 13, 187–220.
7. Girosi, F., & Anzellotti, G. (1993). Rates of convergence for radial basis functions and neural networks. In R. J. Mammone (Ed.), Artificial neural networks for speech and vision (pp. 97–113). London: Chapman & Hall.
8. Gurvits, L., & Koiran, P. (1997). Approximation and learning of convex superpositions. J. Computer and System Sciences, 55, 161–170.
9. Hewitt, E., & Stromberg, K. (1965). Real and abstract analysis. New York: Springer Verlag.
10. Ito, Y. (1991). Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Networks, 4, 385–394.
11. Jones, L. K. (1992). A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Annals of Statistics, 20, 608–613.
12. Kainen,P.C.,&Kůrková, V. (2008). Estimates of network complexity and integral representations. In V. Kůrková, R. Neruda, & J. Koutník (Eds.), Artificial neural networks—ICANN 2008 (pp. 31–40). Berlin: Springer-Verlag.
13. Kainen, P. C., Kůrková, V., & Sanguineti, M. (2009). Estimates of approximation rates by gaussian radial-basis functions. Journal of Complexity, 25, 63–74.
14. Kainen, P. C., Kůrková, V., & Vogt, A. (2007). A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves. Journal of Approximation Theory, 147, 1–10.
15. Kainen,P.C.,Kůrková, V., & Vogt, A. (forthcoming). Integral combinations of Heavisides. Mathematische Nachrichten.
16. Kůrková, V. (1997). Dimension–independent rates of approximation by neural networks. In K. Warwick & M. Kárný (Eds.), Computer-intensive methods in control and signal processing: Curse of dimensionality (pp. 261–270). Boston: Birkhauser.
17. Kůrková, V. (2003). High-dimensional approximation and optimization by neural networks. In J. Suykens, G. Horváth, S. Basu, C. Micchelli, & J. Vandewalle (Eds.), Advances in learning theory: Methods, models and applications (pp. 69–88). Amsterdam: IOS Press.
18. Kůrková, V., Kainen, P. C., & Kreinovich, V. (1997). Estimates of the number of hidden units and variation with respect to half-spaces. Neural Networks, 10, 1061–1068.
19. Kůrková, V., & Sanguineti, M. (2005). Error estimates for approximate optimization by the extended Ritz method. SIAM J. Optimization, 2(15), 461–487.
20. Martínez, C., & Sanz, M. (2001). The theory of fractional powers of operators. Amsterdam: Elsevier.
21. Pisier, G. (1981). Remarques sur un resultat non publié deB.Maurey. Seminaire d’Analyse Fonctionelle 1980–81, no. 5, 1–12.
22. Zaanen, A. C. (1961). An Introduction to the Theory of Integration. Amsterdam: North Holland.