Convergence Analysis of Continuous-Time Neural Networks

  • Min-Jae Kang
  • Ho-Chan Kim
  • Farrukh A. Khan
  • Wang-Cheol Song
  • Jacek M. Zurada
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3971)

Abstract

The energy function of continuous-time neural network has been analyzed for testing the existence of stationary points and the global convergence of network. The energy function always has only one stationary point which is a saddle point in the unconstrained space when the total conductance of neuron’s input is zero (Gi = 0). However, the stationary points exist only inside the hypercube Rn ∈[0,1] when the total conductance of neuron’s input is not zero (Gi ≠ 0). The Hessian matrix of the energy function is used for testing the global convergence of the network.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hopfield, J.J., Tank, D.W.: Neural Computation of Decisions in Optimization Problems. Biological Cybernetics 52, 141–152 (1985)MATHMathSciNetGoogle Scholar
  2. 2.
    Hopfield, J.J., Tank, D.W.: Computing with Neural Circuits: A Model. Science 233, 625–633 (1986)CrossRefGoogle Scholar
  3. 3.
    Friedberg, S., Insel, A.: Introduction to Linear Algebra with Application, 1st edn. Prentice-Hall, Englewood Cliffs (1986)Google Scholar
  4. 4.
    Michel, A.N., Farrel, J.A., Porod, W.: Qualitative Analysis of Neural Networks. IEEE Trans. Circuits Systems 36, 229–243 (1989)MATHCrossRefGoogle Scholar
  5. 5.
    Zurada, J.M.: Introduction to Artificial Neural Systems, 1st edn. West, St. Paul MN (1992)Google Scholar
  6. 6.
    Peng, M., Gupta, N., Armitage, A.F.: An investigation into the Improvement of Local Minima of the Hopfield Network. Neural Networks 9(7), 1241–1253 (1996)CrossRefGoogle Scholar
  7. 7.
    Golub, G.H., Van Loan, C.F.: Matrix Computations, 3rd edn. John Hopkins Univ. Press, Baltimore (1996)Google Scholar
  8. 8.
    Chen, T., Amari, S.I.: Stability Asymmetric Hopfield Networks. IEEE Trans. Neural Networks 12(1), 159–163 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Min-Jae Kang
    • 1
  • Ho-Chan Kim
    • 1
  • Farrukh A. Khan
    • 2
  • Wang-Cheol Song
    • 2
  • Jacek M. Zurada
    • 3
  1. 1.Faculty of Electrical & Electronic EngineeringCheju National UniversityJejuSouth Korea
  2. 2.Department of Computer EngineeringCheju National UniversityJejuSouth Korea
  3. 3.Department of Electrical EngineeringUniversity of LouisvilleLouisvilleUSA

Personalised recommendations