A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves

Journal of Approximation Theory

Volumn 147, Issue 1, 2007, Pages 1-10

  Kainen, Paul C ^a   Kůrková, Věra ^b   Vogt, Andrew ^a  

^a GEORGETOWN UNIVERSITY   (United States)

^b INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

Author keywords

Characteristic functions of closed half spaces; Gaussian function; Integral formulas; Perceptron neural networks; Radon transform; Rates of approximation; Variation with respect to half spaces

Indexed keywords

EID: 34447641642     PISSN: 00219045     EISSN: 10960430     Source Type: Journal    
DOI: 10.1016/j.jat.2006.12.009     Document Type: Article

References (32)

1. Abramowitz M., and Stegun I.A. Handbook of Mathematical Functions (1973), 8th Dover Printing (10th of GPO), New York
2. Adams R.A., and Fournier J.J.F. Sobolev Spaces. second ed. (2003), Academic Press, Amsterdam
3. Andrews G.E., Askey R., and Roy R. Special Functions (1999), Cambridge University Press, Cambridge
4. A.R. Barron, Neural net approximation, in: Proceedings of the Seventh Yale Workshop on Adaptive and Learning Systems, 1992, pp. 69-72.
5. Barron A.R. Universal approximation bounds for superposition of a sigmoidal function. IEEE Trans. Inform. Theory 39 (1993) 930-945
6. Carroll S.M., and Dickinson B.W. Construction of neural nets using the Radon transform. Proceedings of IJCNN (1989), IEEE Press, New York 607-611
7. Cheang G.H.L., and Barron A.R. A better approximation for balls. J. Approx. Theory 104 (2000) 183-203
8. Courant R. Differential and Integral Calculus vol. 2 (1936), Wiley, New York (1964 ed., transl. E.J. McShane)
9. Courant R., and Hilbert D. Methods of Mathematical Physics vol. 1 (1989), Wiley, New York
10. Edwards C.H. Advanced Calculus of Several Variables (1994), Dover, New York
11. F. Girosi, Approximation error bounds that use VC-bounds, in: Proceedings of the International Conference on Artificial Neural Networks (ICANN'95), EC2 & Cie, Paris, 1995, pp. 295-302.
12. Girosi F., and Anzellotti G. Rates of convergence for radial basis function and neural networks. Artificial Neural Networks for Speech and Vision (1993), Chapman & Hall, London 97-113
13. Gurvits L., and Koiran P. Approximation and learning of convex superpositions. J. Comput. System Sci. 55 (1997) 161-170
14. Helgason S. The Radon Transform (1980), Birkhäuser, Boston
15. Ito Y. Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Networks 4 (1991) 385-394
16. Jones L.K. A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Ann. Statist. 20 (1992) 608-613
17. Kainen P.C., Kůrková V., and Vogt A. Geometry and topology of continuous best and near best approximations. J. Approx. Theory 105 (2000) 252-262
18. Kainen P.C., Kůrková V., and Vogt A. An integral formula for Heaviside neural networks. Neural Network World 3 (2000) 313-319
19. Kainen P.C., Kůrková V., and Vogt A. Best approximation by Heaviside perceptron networks. Neural Networks 13 (2000) 695-697
20. P.C. Kainen, V. Kůrková, A. Vogt, Integral combinations of Heavisides, 2005, submitted for publication (see ftp.cs.cas.cz/pub/reports/v968-06.pdf).
21. Kon M.A., Raphael L.A., and Williams D.A. Extending Girosi's approximation estimates for functions in Sobolev spaces via statistical learning theory. J. Anal. Appl. 3 (2005) 67-90
22. Kůrková V. Dimension-independent rates of approximation by neural networks. In: Warwick K., and Kárný M. (Eds). Computer-Intensive Methods in Control and Signal Processing: Curse of Dimensionality (1997), Birkhauser, Boston 261-270
23. Kůrková V. High-dimensional approximation and optimization by neural networks. In: Suykens J., et al. (Ed). Advances in Learning Theory: Methods, Models and Applications (2003), IOS Press, Amsterdam 69-88 (Chapter 4)
24. Kůrková V., Kainen P.C., and Kreinovich V. Estimates of the number of hidden units and variation with respect to half-spaces. Neural Networks 10 (1997) 1061-1068
25. Kůrková V., and Sanguineti M. Comparison of worst-case errors in linear and neural network approximation. IEEE Trans. Inform. Theory 48 (2002) 264-275
26. Makovoz Y. Uniform approximation by neural networks. J. Approx. Theory 95 (1998) 215-228
27. Mhaskar H.N., and Micchelli C.A. Dimension independent bounds on the degree of approximation by neural networks. IBM J. Res. Develop. 38 (1994) 277-284
28. Natanson I.P. Theory of Functions of a Real Variable vol. I (1961), Ungar, New York (Transl. L.F. Boron with editorial annotations by E. Hewitt)
29. A. Pinkus, Approximation theory of the MLP model in neural networks, Acta Numer., 1999, 143-195.
30. G. Pisier, Remarques sur un résultat non publié de B. Maurey, in: Séminaire d'Analyse Fonctionnelle 1980-81, Exposé, no. V, École Polytechnique, Centre de Mathématiques, Palaiseau, France, 1980, pp. V.1-V.12.
31. Szász O. On the relative extrema of the Hermite orthogonal functions. J. Indian Math. Soc. 25 (1951) 129-134
32. Szego{combining double acute accent} G. Orthogonal Polynomials (1975), American Mathematical Society Colloquium Series XXIII, Providence, RI