Skip to main content
Springer Nature Link
Log in

Networks and closed balls

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

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

Neural networks calledtangent networks are constructed by explicit reference to the geometry of a set, and then blended intocascades which approximate characteristic functions of closed balls. In this way some known results about approximation by single hidden layer neural networks are re-proved in a very constructive and geometrical fashion.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. E. Artin,The Gamma Function, Holt, Rinehart and Winston, 1964.

  2. A.R. Barron, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Trans. Inf. Theory 39, 1993, 930–945.

    Article  Google Scholar 

  3. D. Chen, Degree of approximation by superpositions of a sigmoidal function, Approx. Theory Appl. 9, 1993, 17–28.

    Google Scholar 

  4. T. Chen et al., A constructive proof and an extension of Cybenko's approximation theorem, in:Computing Science and Statistics, Proceedings of the Second Symposium on the Interface, Springer, 1992.

  5. C.K. Chui and X. Li, Realization of neural networks with one hidden layer, in:Multivariate Approximation: From CAGD to Wavelets, eds. K. Jetter and F.I. Utreras, World Scientific, 1993, pp. 77–89.

  6. G. Cybenko, Approximation by superposition of sigmoidal functions, Math. Control, Signals, Syst. 2, 1989, 303–314.

    Google Scholar 

  7. K. Funahashi, On the approximate realization of continuous mappings by neural networks, Neural Networks 2, 1989, 183–192.

    Article  Google Scholar 

  8. S. Gallot, D. Hulin and J. Lafontaine,Riemannian Geometry, Springer, 1990.

  9. P.R. Halmos,Measure Theory, Van Nostrand, 1950.

  10. S.G. Lim, M.D. Alder and P. Hadingham, Adaptive quadratic neural nets, Pattern Recognition Lett. 13, 1992, 325–329.

    Article  Google Scholar 

  11. L. Hörmander,The Analysis of Linear Partial Differential Operators I, Springer, 1983.

  12. H.N. Mhaskar and C.A. Micchelli, Approximation by superposition of sigmoidal and radial basis functions, Adv. Appl. Math. 13, 1992, 350–373.

    Article  Google Scholar 

  13. H.N. Mhaskar and C.A. Micchelli, Degree of approximation by neural and translation networks with a single hidden layer, preprint, 1995.

  14. F.W.J. Olver,Asymptotics and Special Functions, Academic Press, 1974.

  15. W. Rudin,Functional Analysis, McGraw-Hill, 1973.

  16. X. Sun and E.W. Cheney, The fundamentality of ridge functions, Aequationes Math. 44, 1992, 226–235.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics, The University of Western Australia, 6907, Nedlands, WA, Australia

    J. Lyle Noakes

Authors
  1. J. Lyle Noakes
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Noakes, J.L. Networks and closed balls. Adv Comput Math 5, 153–161 (1996). https://doi.org/10.1007/BF02124740

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02124740

Keywords

Search

Navigation