Functions bandlimited in frequency are free of the curse of dimensionality

Neurocomputing

Volumn 70, Issue 7-9, 2007, Pages 1439-1452

  Ignacio Mulero Martínez, Juan ^a  

^a TECHNICAL UNIVERSITY OF CARTAGENA   (Spain)

Author keywords

Bandlimited functions; Curse of dimensionality; Radial basis functions; Sampling theory; Truncation errors

Indexed keywords

APPROXIMATION THEORY; FOURIER ANALYSIS; GAUSSIAN DISTRIBUTION; SAMPLING;

BANDLIMITED FUNCTIONS; DIMESIONALITY; RADIAL BASIS FUNCTIONS; TRUNCATION ERRORS;

RADIAL BASIS FUNCTION NETWORKS;

ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER ANALYSIS; FOURIER ANALYSIS; FREQUENCY ANALYSIS; INFORMATION PROCESSING; NORMAL DISTRIBUTION; PRIORITY JOURNAL; SIGNAL PROCESSING;

EID: 33847416637     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2006.05.010     Document Type: Article

References (40)

1. Barron A.R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory 39 3 (1993) 930-945
2. Bellman R.E. Adaptive Control Processes (1961), Princeton University Press, Princeton, NJ
3. Brown J.W., and Churchill R.V. Complex Variables and Applications. seventh ed. (2003), McGraw-Hill Science, New York
4. Bruna J., Massaneda X., and Ortega-Cerdà J. Connections between signal processing and complex analysis. Contrib. Sci. 2 3 (2003) 345-357
5. Chen G., and Fang G. The discrete characterization of Paley-Wiener space with several variables. Prog. Nat. Sci. 13 (2003) 300-303
6. Cotter N.E. The Stone-Weierstrass theorem and its application to neural networks. IEEE Trans. Neural Networks 1 4 (1990) 290-295
7. Cybenko G. Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2 4 (1989) 303-314
8. A.T. Dingankar, On applications of approximation theory to identification, control and classification, Ph.D. Thesis, University of Texas, 1995.
9. Fang G. Whittaker-Kotelnikov-Shannnon sampling theorem and aliasing error. J. Approx. Theory 85 (1996) 115-131
10. Fine T.L. Feedforward neural network methodology, Statistics for Engineering and Information Science (1999), Springer, Berlin
11. Funahashi K.-I. On the approximate realization of continuous mappings by neural networks. Neural Networks 2 (1989) 183-192
12. F. Girosi, G. Anzellotti, Convergence rates of approximation by translates, Technical Report A.I. Memo No. 1288. C.B.I.P. Paper No. 73, MIT Artificial Intelligence Laboratory and Center for Biological Information Processing Whitaker College, April 1995.
13. Higgins J.R. Five short stories about the cardinal series. Bull Am. Math. Soc. 12 (1985) 45-89
14. Hinsen G. Irregular sampling of bandlimited lp-functions. J. Approx. Theory 72 (1993) 346-364
15. Hlávácková-Schindler K., and Sanguineti M. Bounds on the complexity of neural-network models and comparison with linear methods. Int. J. Adapt. Control Signal Process 17 (2003) 179-194
16. Horn R.A., and Johnson C.R. Matrix Analysis (1999), Cambridge University Press, Cambridge
17. Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Networks 4 (1991) 251-257
18. Hornik K., Stinchcombe M., and White H. Multilayer feedforward networks are universal approximators. Neural Networks 2 (1989) 359-366
19. Kallkuhl J., Hunt K.J., Zbikowski R., and Dzielinshi A.J. Applications of Neural Adaptive Control Technology (1997), World Scientific, Singapore
20. Kowalski M.A. Optimal complexity recovery of band- and energy-limited signals. J. Complexity 2 3 (1986) 239-254
21. Kowalski M.A., and Stenger F. Optimal complexity recovery of band- and energy-limited signals II. J. complexity 5 1 (1989) 45-59
22. Kuhn T.S., Lyubarskii Y., Sodin M., and Tkachenko V. The Structure of Scientific Revolutions. third ed. (1996), University Of Chicago Press
23. Levin B.Y., Lyubarskii Y., Sodin M., and Tkachenko V. Lectures on Entire Functions. American Mathematical Society (1996)
24. Mhaskar H.N. On the representation of band limited functions using finitely many bits. J. Complexity 18 2 (2002) 449-478
25. Mhaskar H.N. When is approximation by Gaussian networks necessarily a linear process?. Neural Networks 17 7 (2004) 989-1001
26. Mhaskar H.N., and Pai D.V. Fundamentals of Approximation Theory (2000), Narosa Publishing House, New York
27. Nikolskii S.M. Approximation of Functions of Several Variables and Imbedding Theorems (1975), Springer, Berlin
28. Oppenheim A.V., and Young I.T. Señales Y Sistemas (1994), Prentice-Hall, Englewood Cliffs, NJ
29. Ortega-Cerdá J., and Seip K. Fourier frames. Ann. Math 155 3 (2002) 789-806
30. Plancherel M., and Pólya G. Functions entières et intégrales de fourier multiples. Comment. Math. Hel. 10 (1937-1938) 110-163
31. Poggio T., and Girosi F. Networks for approximation and learning. Proc. IEEE 78 9 (1990) 1481-1497
32. Sadegh N. A perceptron network for functional identification and control of nonlinear systems. IEEE Trans. Neural Networks 4 6 (1993) 982-988
33. Sanner R.M., and Slotine J.E. Gaussian networks for direct adaptive control. IEEE Trans. Neural Networks 3 (1992) 837-863
34. Shannon C.E. Communication in the presence of noise. Proc. IEEE 86 2 (1998) 447-457 classic paper.
35. Spiegel M.R. Schaum's Outline of Complex Variables. first ed. (1968), McGraw-Hill, New York
36. Stein E.M., and Guido W. Introduction to Fourier Analysis on Euclidean Spaces. sixth ed. (1990), Princeton University Press, Princeton, NJ
37. Unser M. Sampling-50 Years after Shannon. Proc. IEEE 88 4 (2000) 569-587
38. Vapnik V.N. Statistical Learning Theory (1998), Wiley, New York
39. Vapnik V.N. The Nature of Statistical Learning Theory (1999), Springer, Berlin
40. R. Zbikowski, K.J. Hunt, Neural Adaptive Control Technology, vol. 15. World Scientific Series in Robotics and Intelligent Systems, 1996.