Skip to main content

Multidimensional Nonlinear Myopic Maps, Volterra Series, and Uniform Neural-Network Approximations

  • Chapter

Abstract

Our main result is a theorem which gives necessary and sufficient conditions under which discrete-space multidimensional myopic input-output maps with vector-valued inputs drawn from a certain large set can be uniformly approximated arbitrarily well using a structure consisting of a linear preprocessing stage followed by a memoryless nonlinear network. Noncausal as well as causal maps are considered. Approximations for noncausal maps for which inputs and outputs are functions of more than one variable are of current interest in connection with, for example, image processing.

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

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD   54.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. V. Volterra, Theory of Functionals and of Integral and Integro-Differential Equations,New York: Dover, 1959.

    MATH  Google Scholar 

  2. M. Schetzen, The Volterra and Wiener Theories of Nonlinear Systems, John Wiley, New York, 1980.

    MATH  Google Scholar 

  3. I. W. Sandberg, “A perspective on system theory”, IEEE Transactions on Circuits and Systems,vol. 31, no. 1, pp. 88–103, January 1984.

    Article  MathSciNet  MATH  Google Scholar 

  4. G. Cybenko, “Approximation by superposition of a single function,” Mathematics of Control, Signals and Systems, vol. 2, pp. 303–314,1989.

    Article  MathSciNet  MATH  Google Scholar 

  5. H. N. Mhaskar and C. A. Micchelli, “ Approximation by superposition of sigmoidal and radial basis functions,” Advances in Applied mathematics,vol. 3, pp. 350–373, 1992.

    Article  MathSciNet  Google Scholar 

  6. T. Chen and H. Chen, “Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its applications to dynamic systems,” IEEE Transactions on Neural Networks, vol. 6, no. 4, pp. 911–917, July 1995.

    Article  Google Scholar 

  7. J. Park and I. W. Sandberg, “Approximation and radial-basis function networks,” Neural Computation, vol. 5, no. 2, pp. 305–316, March 1993.

    Article  Google Scholar 

  8. I. W. Sandberg, “Structure theorems for nonlinear systems,” Multidimensional Systems and Signal Processing, vol. 2, no. 3, pp. 267–286, 1991. (See also the Errata in vol. 3, no. 1, p. 101, 1992.) A conference version of the paper appears in Integral Methods in Science and Engineering-90 (Proceedings of the International Conference on Integral Methods in Science and Engineering, Arlington, Texas, May 1518, 1990, ed. A. H. Haji-Sheikh), New York: Hemisphere Publishing, pp. 92–110, 1991.

    Google Scholar 

  9. I. W. Sandberg, “Uniform approximation and the circle criterion,” IEEE Transactions on Automatic Control, vol. 38, no. 10, pp. 1450–1458, October 1993.

    Article  MathSciNet  MATH  Google Scholar 

  10. I. W. Sandberg, “Approximately-finite memory and input-output maps,” IEEE Transactions on Circuits and Systems-I, vol. 39, no. 7, pp. 549–556, July 1992.

    Article  MATH  Google Scholar 

  11. I. W. Sandberg and L. Xu, “Network approximation of input-output maps and functionals,” to appear in the Journal of Circuits, Systems, and Signal Processing, 1996.

    Google Scholar 

  12. T. Chen and H. Chen, “Approximations of continuous functionals by neural networks with application to dynamical systems,” IEEE Transactions on Neural Networks, vol. 4, no. 6, pp. 910–918, November 1993.

    Article  Google Scholar 

  13. S. Boyd and L. O. Chua, “Fading memory and the problem of approximating nonlinear operators with volterra series,” IEEE Transactions on Circuits and Systems, vol. CAS-32, no. 11, pp. 1150–1161, November 1985.

    Article  MathSciNet  Google Scholar 

  14. I. W. Sandberg and L. Xu, “Uniform approximation of multidimensional myopic maps,” submitted. (A conference version is to appear in the Proceedings of the Volterra Centennial Symposium, Department of Mathematics, University of Texas at Arlington, May 1996.)

    Google Scholar 

  15. B. De Vries, J. C. Principe, and P. Guedes de Oliveira, “Adaline with adaptive recursive memory,” Proceedings of IEEE-SP Workshop on Neural Networks for Signal Processing, pp. 101–110, 1991.

    Google Scholar 

  16. I. W. Sandberg and L. Xu, “Gamma networks and the uniform approximation of input-output maps,” Proceedings of Circuits, Systems, and Computers ‘86, Hellenic Naval Academy, Piraeus, Greece, July 1996 (to appear).

    Google Scholar 

  17. M. H. Stone, “A generalized Weierstrass approximation theorem,” In Studies in Modern Analysis, ed. R. C. Buck, vol. 1 of MAA Studies in Mathematics, pp. 30–87, Prentice-Hall, Englewood Cliffs, NJ, March 1962.

    Google Scholar 

  18. W. Rudin, Principles of Mathematical Analysis, McGraw-Hill, New York, 1976.

    MATH  Google Scholar 

  19. L. A. Liusternik and V. J. Sobolev, Elements of Functional Analysis, Frederick Ungar Publishing Co., New York, 1961.

    Google Scholar 

  20. J. Dieudonné, Foundations of Modern Analysis, Academic Press, New York, 1969.

    MATH  Google Scholar 

  21. J. G. Proakis and D. G. Manolakis, Digital Signal Processing, second edition, New York: Macmillan, 1992.

    MATH  Google Scholar 

  22. L. B. Jackson, Signals, Systems,and Transforms, New York: Addison-Wesley, 1991.

    Google Scholar 

  23. L. V. Kantorovich and G. P. Akilov, Functional Analysis,Oxford: Pergamon, 1982.

    MATH  Google Scholar 

  24. G. Bachman and L. Narici, Functional Analysis,New York: Academic Press, 1966.

    MATH  Google Scholar 

  25. I. W. Sandberg, “A Representation theorem for linear systems,” submitted.

    Google Scholar 

  26. D. Ball and I. W. Sandberg, “ g-and h- Representations for Nonlinear Maps,” J. Mathematical Analysis and Applications, Vol. 149, No. 2, July 1990.

    Article  MathSciNet  Google Scholar 

  27. I. W. Sandberg, “Notes on uniform approximation of time-varying systems on finite time intervals,” submitted. A conference version appears in Proceedings of the Fourth International Workshop on Nonlinear Dynamics of Electronic Systems, Seville, Spain, pp. 149–154, June 1996.

    Google Scholar 

  28. A. Dingankar and I. W. Sandberg, “Network approximation of dynamical systems,” Proceedings of the 1995 International Symposium on Nonlinear Theory and its Applications, vol. 2, pp. 357–362, Las Vegas, December 1995.

    Google Scholar 

Download references

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer Science+Business Media New York

About this chapter

Cite this chapter

Sandberg, I.W. (1997). Multidimensional Nonlinear Myopic Maps, Volterra Series, and Uniform Neural-Network Approximations. In: Docampo, D., Figueiras-Vidal, A.R., Pérez-González, F. (eds) Intelligent Methods in Signal Processing and Communications. Birkhäuser, Boston, MA. https://doi.org/10.1007/978-1-4612-2018-3_5

Download citation

  • DOI: https://doi.org/10.1007/978-1-4612-2018-3_5

  • Publisher Name: Birkhäuser, Boston, MA

  • Print ISBN: 978-1-4612-7383-7

  • Online ISBN: 978-1-4612-2018-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics