Advertisement

ICANN ’93 pp 704-706 | Cite as

A Novel Liapunov Function for Additive Neural Networks

  • Alexander N. Jourjine
Conference paper

Abstract

Using the properties of nonlinear integral equations of the Hammerstein type, it is proven that a new Liapunov function for additive neural networks exists, provided two conditions on symmetry and positivity of the weight matrix hold. The function does not require monotonicity of the transfer function.

Keywords

Transfer Function Symmetric Part Absolute Stability Mathematical Literature Nonlinear Integral Equation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Hopfield, J. J., Neurons with Collective Response Have Collective Computational Properties Like Those of Two-State Neurons, Proc Nat Acad Sci, USA, 81, (1984), pp. 3088–3092CrossRefGoogle Scholar
  2. [2]
    Cohen, M. A., Grossberg, S., Absolute Stability of Global Pattern Formation and Parallel Memory Storage by Competitive Neural Networks, IEEE Trans on Systems, Man and Cyb., 13, (1983), pp. 815–826MathSciNetCrossRefMATHGoogle Scholar
  3. [3]
    Hammerstein, A., Nichtlineare Integralgleichungen nebst Anwendungen, Acta Math. 54, (1930), pp. 117–176MathSciNetCrossRefMATHGoogle Scholar
  4. [4]
    Krasnosel’skii, M., Topological Methods in the Theory of Nonlinear Integral Equations, Pergamon Press, Oxford, 1965Google Scholar
  5. [5]
    Rall, L. B., Variational Methods for Nonlinear Integral Equations, in Anselone, P.M., Ed, Nonlinear Integral Equations; Proceedings of an Advanced Seminar at the University of Wisconsin, University of Wisconsin Press, Madison, 1964, pp. 155–189Google Scholar
  6. [6]
    Tricomi, F. G., Integral Equations, Chap 4, John Wiley/Interscience, New York, 1957MATHGoogle Scholar
  7. [7]
    Jourjine, A. N., Large n Limit of Additive Neural Networks, Proceedings of Neuro-Nimes ‘92, Nimes, France, November 1992, pp. 635–643Google Scholar
  8. [8]
    Kelly, D. G., Stability in Contractive Nonlinear Neural Networks, IEEE Trans Biomed Eng 37, (1990), p.p. 231–242.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1993

Authors and Affiliations

  • Alexander N. Jourjine
    • 1
  1. 1.Wang LaboratoriesAdvanced TechnologyLowellUSA

Personalised recommendations