Nonparametric regression estimation by normalized radial basis function networks

IEEE Transactions on Information Theory

Volumn 51, Issue 3, 2005, Pages 1003-1010

  Krzyzak, Adam ^a   Schäfer, Dominik ^b  

^a Dept of Electrical and Computer Engineering   (Canada)

^b UNIVERSITY OF STUTTGART   (Germany)

Author keywords

Covering numbers; Empirical risk minimization; Nonparametric regression estimation; Normalized radial basis function networks.

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; EIGENVALUES AND EIGENFUNCTIONS; ERROR ANALYSIS; MATHEMATICAL MODELS; OPTIMIZATION; PROBABILITY; REGRESSION ANALYSIS; THEOREM PROVING;

COVERING NUMBERS; EMPIRICAL RISK MINIMIZATION; NONPARAMETRIC REGRESSION ESTIMATION; NORMALIZED RADIAL BASIS FUNCTION NETWORKS;

NEURAL NETWORKS;

EID: 15244362346     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIT.2004.842632     Document Type: Article

References (29)

1. M. Anthony and P. L. Bartlett, Neural Network Learning: Theoretical Foundations. Cambridge, U.K.: Cambridge Univ. Press, 1999.
2. A. R. Barron, "Universal approximation bounds for superpositions of a sigmoidal function," IEEE Trans. Inf. Theory, vol. 39, no. 3, pp. 930-945, May 1993.
3. G. Cybenko, "Approximations by superpositions of sigmoidal functions," Math. Contr., Signals, Syst., vol. 2, pp. 303-314, 1989.
4. L. Devroye, "Automatic pattern recognition: A study of the probability of error," IEEE Trans. Pattern Anal. Mach. Intell., vol. 10, no. 4, pp. 530-543, Jul. 1988.
5. L. Devroye, L. Györfi, and G. Lugosi, Probabilistic Theory of Pattern Recognition. New York: Springer-Verlag, 1996.
6. [i#m-splines," RAIRO Anal. Numér., vol. 12, no. 4, pp. 325-334, 1978.
7. A. Faragó and G. Lugosi, "Strong universal consistency of neural network classifiers," IEEE Trans. Inf. heory, vol. 39, no. 4, pp. 1146-1151, Jul. 1993.
8. F. Girosi and G. Anzellotti, "Rates of convergence for radial basis functions and neural networks," in Artificial Neural Networks for Speech and Vision, R. J. Mammone, Ed. London, U.K.: Chapman and Hall, 1993. pp. 97-113.
9. F. Girosi, M. Jones, and T. Poggio, "Regularization theory and neural network architectures," Neural Comput., vol. 7, pp. 219-267, 1995.
10. U. Grenander, Abstract Inference. New York: Wiley, 1981.
11. L. Györfi, M. Kohler, A. Krzyzak, and H. Walk, A Distribution-Free Theory of Nonparametric Regression. New York: Springer-Verlag, 2002.
12. D. Haussler, "Decision theoretic generalizations of the PAC model for neural net and other learning applications," Inform. Comput., vol. 100, pp. 78-150, 1992.
13. K. Hornik, S. Stinchcombe, and H. White, "Multilayer feed-forward networks are universal approximators," Neural Netw., vol. 2, pp. 359-366, 1989.
14. A. N. Kolmogorov and V. M. Tihomirov, "ε-entropy and ε-capacity of sets in function spaces," Transl. Amer. Math. Soc., vol. 17, pp. 277-364, 1961.
15. A. Krzyzak, T. Linder, and G. Lugosi, "Nonparametric estimation and classification using radial basis function nets and empirical risk minimization," IEEE Trans. Neural Netw., vol. 7, no. 2, pp. 475-487, Mar. 1996.
16. A. Krzyzak and T. Linder, "Radial basis function networks and complexity regularization in function learning," IEEE Trans. Neural Netw., vol. 9, no. 2, pp. 247-256, Mar. 1998.
17. A. Krzyzak and H. Niemann, "Convergence and rates of convergence of radial basis functions networks in function learning," Nonlin. Anal. vol. 47, pp. 281-292, 2001.
18. A. Krzyzak and D. Schäfer, "Nonparametric Regression Estimation by Normalized Radial Basis Function Networks," Universität Stuttgart, Mathematisches Institut A, Stuttgart, Germany, Preprint 2002-15, 2002.
19. G. Lugosi and K. Zeger, "Nonparametric estimation via empirical risk minimization," IEEE Trans. Inf. Theory., vol. 41, no. 3, pp. 677-687, May 1995.
20. J. Moody and J. Darken, "Fast learning in networks of locally-tuned processing units," Neural Comput., vol. 1, pp. 281-294, 1989.
21. J. Park and I. W. Sandberg, "Universal approximation using radial-basis-function networks," Neural Comput., vol. 3, pp. 246-257, 1991.
22. J. Park, I.W. Sandberg, "Approximation and radial-basis-function networks," Neural Comput., vol. 5, pp. 305-316, 1993.
23. D. Pollard, Convergence of Stochastic Processes. New York: Springer-Verlag, 1984.
24. R. Shorten and R. Murray-Smith, "Side effects of normalizing radial basis function networks," Int. J. Neural Syst., vol. 7, pp. 167-179, 1996.
25. D. F. Specht, "Probabilistic neural networks," Neural Netw., vol. 3, pp. 109-118, 1990.
26. V. N. Vapnik and A. Y. Chervonenkis, "On the uniform convergence of relative frequencies of events to their probabilities," Theory Probab. its Applic., vol. 16, pp. 264-280, 1971.
27. V. N. Vapnik, Estimation of Dependences based on Empirical Data, 2nd ed. New York: Springer-Verlag, 1999.
28. H. White, "Connectionist nonparamemetric regression: Multilayer feedforward networks that can learn arbitrary mappings," Neural Netw., vol. 3, pp. 535-549, 1990.
29. L. Xu, A. Krzyzak, and A. L. Yuille, "On radial basis function nets and kernel regression: Approximation ability, convergence rate and receptive field size," Neural Netw., vol. 7, pp. 609-628, 1994.