When is approximation by Gaussian networks necessarily a linear process?

Neural Networks

Volumn 17, Issue 7, 2004, Pages 989-1001

  Mhaskar, H N ^a  

^a CALIFORNIA STATE UNIVERSITY   (United States)

Author keywords

Converse theorems; Gaussian networks; Hermite polynomials; Weighted polynomial approximation

Indexed keywords

APPROXIMATION THEORY; FUNCTIONS; INTERPOLATION; LINEAR SYSTEMS;

GAUSSIAN NETWORKS; LINEAR PROCESSES;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; CELL COUNT; LINEAR SYSTEM; NERVE CELL; NONLINEAR SYSTEM; PRIORITY JOURNAL;

HUMANS; LINEAR MODELS; NEURAL NETWORKS (COMPUTER); NEURONS; NORMAL DISTRIBUTION;

EID: 4143117111     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2004.04.001     Document Type: Article

References (15)

1. DeVore R., Howard R., Micchelli C.A. Optimal nonlinear approximation. Manuscripta Mathematica. 63:1989;469-478
2. Dyn N. Interpolation and approximation by radial and related functions. Chui C.K., Schumaker L.L., Ward J.D. Approximation Theory. 1989;211-234 Academic Press, New York
3. Freud G. Direct and converse theorems in the theory of weighted polynomial approximation. Math. Zeitschrift. 126:1972;123-134
4. Girosi F., Anzellotti G. Rates of convergence for radial basis functions and neural networks. Mammone R.J. Artificial neural networks for speech and vision. 1993;97-113 Chapman & Hall, London
5. Kurkova V., Sanguineti M. Bounds on rates of variable basis and neural network approximation. IEEE Transactions on Information Theory. 47:2001;2659-2665
6. Kurkova V., Sanguineti M. Comparison of worst case errors in linear and neural network approximation. IEEE Transactions on Information Theory. 48:2002;264-275
7. Lorentz G.G. Approximation of functions. 1966;Rinehart and Winston, New York
8. Mhaskar H.N. Introduction to the theory of weighted polynomial approximation. 1996;World Scientific, Singapore
9. Mhaskar H.N. On the degree of approximation in multivariate weighted approximation. Buhmann M.D., Mache D.H. Advanced Problems in Constructive Approximation. Proceedings of the IDOMAT 2001 conference, ISNM 142. 2002;129-141 Birkhäuser, Basel
10. Mhaskar H.N. On the representation of band limited functions using finitely many bits. Journal of Complexity. 18:(2):2002;449-478
11. Micchelli C.A. Interpolation of scattered data: distance matrices and conditionally positive definite functions. Constructive Approximation. 2:1986;11-22
12. Narcowich F., Ward J.D. Norm estimates for the inverses of a general class of scattered data radial function interpolation matrices. Journal of Approximation Theory. 69:1992;84-109
13. Park J., Sandberg I.W. Universal approximation using radial basis function networks. Neural Computation. 3:1991;246-257
14. Rudin W. Real and complex analysis. 1974;McGraw Hill, New York
15. Szegö G. Orthogonal polynomials. American Mathematical Society Colloquium Publication 23, American Mathematical Society, Providence. 1975