Complexity estimates based on integral transforms induced by computational units

Neural Networks

Volumn 33, Issue , 2012, Pages 160-167

  Kůrková, Věra ^a  

^a INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

Author keywords

Approximation from a dictionary; Estimates of model complexity; Integral transforms; Neural networks; Norms induced by computational units

Indexed keywords

COMPLEXITY ESTIMATES; COMPUTATIONAL UNITS; INTEGRAL TRANSFORM; MODEL COMPLEXITY; NETWORK COMPLEXITY; NONLINEAR APPROXIMATION THEORY; PERCEPTRON NETWORK;

APPROXIMATION THEORY; ESTIMATION; INTEGRAL EQUATIONS; INTEGRODIFFERENTIAL EQUATIONS; NEURAL NETWORKS;

COMPUTATIONAL COMPLEXITY;

ARTICLE; ARTIFICIAL NEURAL NETWORK; FUNCTIONAL ASSESSMENT; INTEGRAL TRANSFORM; MATHEMATICAL ANALYSIS; MATHEMATICAL COMPUTING; MATHEMATICAL MODEL; MATHEMATICAL PARAMETERS; NONLINEAR SYSTEM; PRIORITY JOURNAL; STATISTICAL ANALYSIS; THEORY;

COMPUTATIONAL BIOLOGY; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS;

EID: 84863873369     PISSN: 08936080     EISSN: 18792782     Source Type: Journal    
DOI: 10.1016/j.neunet.2012.05.002     Document Type: Article

References (40)

1. Adams R.A., Fournier J.J.F. Sobolev spaces 2003, Academic Press, Amsterdam.
2. Barron A.R. Neural net approximation. Proc. 7th Yale workshop on adaptive and learning systems 1992, Yale University Press. K. Narendra (Ed.).
3. Barron A.R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transactions on Information Theory 1993, 39:930-945.
4. Bernstein S.N. Sur le maximum absolu d'une somme trigonométrique. Comptes Rendus de l'Academie des Sciences, Serie I (Mathematique) 1931, 193:433-436.
5. Carroll, S. M., & Dickinson, B. W. (1989). Construction of neural net using the Radon transform. In Proceedings of IJCN. Vol. I (pp. 607-611).
6. Darken C., Donahue M., Gurvits L., Sontag E. Rate of approximation results motivated by robust neural network learning. Proceedings of the sixth annual ACM conference on computational learning theory 1993, 303-309. The Association for Computing Machinery, New York.
7. DeVore R.A., Lorentz G.G. Constructive approximation 1993, Springer-Verlag, Berlin.
8. Donahue M., Gurvits L., Darken C., Sontag E. Rates of convex approximation in non-Hilbert spaces. Constructive Approximation 1997, 13:187-220.
9. Fine T. Feedforward neural network methodology 1999, Springer, New York.
10. Friedman A. Modern analysis 1982, Dover, New York.
11. Girosi, F. (1995). Approximation error bounds that use VC-bounds. In Proceedings of ICANN 1995 (pp. 295-302).
12. Girosi F., Anzellotti G. Rates of convergence for radial basis functions and neural networks. Artificial neural networks for speech and vision 1993, 97-113. Chapman & Hall. R.J. Mammone (Ed.).
13. Gurvits L., Koiran P. Approximation and learning of convex superpositions. Journal of Computer and System Sciences 1997, 55:161-170.
14. Ito Y. Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Networks 1991, 4:385-394.
15. Jones L.K. A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Annals of Statistics 1992, 20:608-613.
16. Kainen P.C., Kůrková V. An integral upper bound for neural network approximation. Neural Computation 2009, 21(10):2970-2989.
17. Kainen P.C., Kůrková V., Sanguineti M. Complexity of Gaussian radial basis networks approximating smooth functions. Journal of Complexity 2009, 25:63-74.
18. Kainen P.C., Kůrková V., Vogt A. A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves. Journal of Approximation Theory 2007, 147:1-10.
19. Kainen P.C., Kůrková V., Vogt A. Integral combinations of Heavisides. Mathematische Nachrichten 2010, 283(6):854-878.
20. Kainen, P. C., & Vogt, A. (2012). Bochner interals and neural networks. In: Bianchini, M. Jain, L. Maggini, M. (Eds.), Handbook on neural information processing. Berlin, Heidelberg: Springer-Verlag (in press).
21. Kůrková V. Dimension-independent rates of approximation by neural networks. Computer-intensive methods in control and signal processing. The curse of dimensionality 1997, 261-270. Birkhäuser, Boston, MA. K. Warwick, M. Kárný (Eds.).
22. Kůrková V. High-dimensional approximation and optimization by neural networks. Advances in learning theory: methods, models and applications 2003, 69-88. IOS Press, Amsterdam, (Chapter 4). J. Suykens, G. Horváth, S. Basu, C. Micchelli, J. Vandewalle (Eds.).
23. Kůrková V. Minimization of error functionals over perceptron networks. Neural Computation 2008, 20(1):252-270.
24. Kůrková V. Model complexity of neural networks and integral transforms. LNCS 2009, Vol. 5768:708-718. Springer-Verlag. M. Polycarpou, C. Panayiotou, C. Alippi, G. Ellinas (Eds.).
25. Kůrková V., Kainen P.C., Kreinovich V. Estimates of the number of hidden units and variation with respect to half-spaces. Neural Networks 1997, 10:1061-1068.
26. Kůrková V., Sanguineti M. Comparison of worst-case errors in linear and neural network approximation. IEEE Transactions on Information Theory 2002, 28:264-275.
27. Kůrková V., Sanguineti M. Error estimates for approximate optimization by the extended Ritz method. SIAM Journal on Optimization 2005, 15:461-487.
28. Kůrková V., Sanguineti M. Geometric upper bounds on rates of variable-basis approximation. IEEE Transactions on Information Theory 2008, 54:5618-5688.
29. Kůrková V., Savický P., Hlaváčková K. Representations and rates of approximation of real-valued Boolean functions by neural networks. Neural Networks 1998, 11:651-659.
30. Lavretsky E. On the geometric convergence of neural approximations. IEEE Transactions on Neural Networks 2002, 13:274-282.
31. Mhaskar H.N. On the tractability of multivariate integration and approximation by neural networks. Journal of Complexity 2004, 20:274-282.
32. Mhaskar H.N. Weighted quadrature formulas and approximation by zonal function networks on the sphere. Journal of Complexity 2006, 22:348-370.
33. Park J., Sandberg I. Universal approximation using radial-basis-function networks. Neural Computation 1991, 3:246-257.
34. Park J., Sandberg I. Approximation and radial-basis-function networks. Neural Computation 1993, 5:305-316.
35. Pietch A. Eigenvalues and s-numbers 1987, Cambridge University Press, Cambridge.
36. Pisier G. Remarques sur un résultat non publié de B. Maurey. École polytechnique 1981, Vol. 12. Centre de Mathématiques, Palaiseau, France.
37. Rudin W. Real and complex analysis 1974, MacGraw-Hill, New York.
38. Schaback R., Wendland H. Kernel techniques: from machine learning to meshless methods. Acta Numerica 2006, 15:543-639.
39. Szabados J. On an interpolatory analogon of the de la vallée poussin means. Studia Scientiarum Mathematicarum Hungarica 1974, 9:187-190.
40. Yoshida K. Functional analysis 1965, Springer-Verlag, Berlin.