Skip to main content
Log in

Approximation properties of zonal function networks using scattered data on the sphere

  • Published:
Advances in Computational Mathematics Aims and scope Submit manuscript

Abstract

A zonal function (ZF) network is a function of the form x↦∑ nk=1 c k \(\phi \)(x · y k), where x and the y k's are on the unit sphere in q+1 dimensional Euclidean space, and where the y k's are scattered points. In this paper, we study the degree of approximation by ZF networks. In particular, we compare this degree of approximation with that obtained with the classical spherical harmonics. In many cases of interest, this is the best possible for a given amount of information regarding the target function. We also discuss the construction of ZF networks using scattered data. Our networks require no training in the traditional sense, and provide theoretically predictable rates of approximation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. R. DeVore, R. Howard and C.A. Micchelli, Optimal nonlinear approximation, Manuscripta Math. 63 (1989) 469-478.

    Article  MathSciNet  Google Scholar 

  2. R. DeVore and G.G. Lorentz, Constructive Approximation (Springer, Berlin, 1994).

    Google Scholar 

  3. K. Jetter, J. Stöckler and J.D. Ward, Error estimates for scattered data interpolation, Math. Comp. 68 (1999) 743-747.

    Article  Google Scholar 

  4. G.G. Lorentz, Approximation of Functions (Holt, Rinehart and Winston, New York, 1966).

    Google Scholar 

  5. H.N. Mhaskar, Approximation of smooth functions by neural networks, in: Dealing with Complexity: A Neural Network Approach, eds. K. Warwick, V. Kurkova and M. Karny (Springer, Berlin, 1997) pp. 189-204.

    Google Scholar 

  6. H.N. Mhaskar and C.A. Micchelli, Degree of approximation by neural and translation networks with a single hidden layer, Adv. Appl. Math. 16 (1995) 151-183.

    Article  MATH  MathSciNet  Google Scholar 

  7. H.N. Mhaskar, F.J. Narcowich and J.D. Ward, Spherical Marcinkiewicz-Zygmund inequalities and positive quadrature, Math. Comp., to appear.

  8. H.N. Mhaskar and J. Prestin, Marcinkiewicz-Zygmund-type inequalities, in: Approximation Theory: In Memory of A.K. Varma, eds. N.K. Govil, R.N. Mohapatra, Z. Nashed, A. Sharma and J. Szabados (Marcel Dekker, New York, 1998).

    Google Scholar 

  9. C. Müller, Spherical Harmonics, Lecture Notes in Mathematics, Vol. 17 (Springer, Berlin, 1966).

    Google Scholar 

  10. S. Pawelke, Über die Approximationsordnung bei Kugelfunktionen und algebraischen Polynomen, Tôhoku Math. J. 24 (1972) 473-486.

    MATH  MathSciNet  Google Scholar 

  11. A. Pinkus, n-widths in Approximation Theory (Springer, New York, 1985).

    Google Scholar 

  12. E.M. Stein, Interpolation in polynomial classes and Markoff's inequality, Duke Math. J. 24 (1957) 467-476.

    Article  MATH  MathSciNet  Google Scholar 

  13. E.M. Stein and G. Weiss, Fourier Analysis on Euclidean Spaces (Princeton University Press, Princeton, NJ, 1971).

    Google Scholar 

  14. G. Szegö, Orthogonal Polynomials, American Mathematical Society Colloquium Publications, Vol. 23 (Amer. Math. Soc., Providence, RI, 1975).

    Google Scholar 

  15. E.T. Whittaker and G.N. Watson, A Course of Modern Analysis (Cambridge University Press, Cambridge, 1965).

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mhaskar, H., Narcowich, F. & Ward, J. Approximation properties of zonal function networks using scattered data on the sphere. Advances in Computational Mathematics 11, 121–137 (1999). https://doi.org/10.1023/A:1018967708053

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1018967708053

Keywords

Navigation