Stability of quasi-periodic orbit in Discrete Recurrent Neural Network

  1. R. L. Marichal 1
  2. J. D. Piñeiro 1
  3. L. Moreno 1
  4. E. J. González 1
  5. J. Sigut 1
  6. S. Alayón 1
  1. 1 Universidad de La Laguna
    info

    Universidad de La Laguna

    San Cristobal de La Laguna, España

    GRID grid.10041.34

Actas:
WSEAS International Conference on Dynamical Systems and Control (1st.2005.Venice)

Editorial: World Scientific and Engineering Academy and Society (WSEAS)

ISBN: 960-8457-37-8

Año de publicación: 2005

Páginas: 586-591

Tipo: Aportación congreso

Exportar: RIS

Resumen

A simple discrete recurrent neural network model is considered. The local stability is analyzed withthe associated characteristic model. In order to study the quasi-periodic orbit dynamic behavior, it is necessary todeterminate the Neimark-Sacker bifurcation. In the case of two neurons, one necessary condition that producesthe Neimark-Sacker bifurcation is found. In addition to this, the stability and direction of the Neimark-Sacker aredetermined by applying the normal form theory and the center manifold theorem. An example is given andnumerical simulation are performed to illustrate the obtained results. The phase-locking is analyzed given someexperimental result of Arnold Tongue in determinate weight configuration.

Referencias bibliográficas

  • C. M. Marcus and R. M. Westervelt, Dynamics of Iterated-Map Neural Networks, Physical Review A, 40, (1989), pp: 501-504 .
  • C. Robinson, Dynamical Systems. Stability, Symbolic Dynamics, and Chaos. Ed. Inc. Press CRC, 1995.
  • D. W. Tank, J.J. Hopfield, Neural computation by concentrating information in time, Proc. Nat. Acad. Sci. USA, 84, (1987), pp: 1896-1991.
  • F. Pasemann. Complex Dynamics and the structure of small neural networks, In Network: Computation in neural system, 13(2), (2002), pp: 195-216.
  • J. Hale, H. Koςak, Dynamics and Bifurcations, Springer-Verlag New York Inc. , 1991.
  • J. Hopfield, Neurons with graded response have collective computational properties like those of two-state neurons, Procs. Nat. Acad. Sci. USA 81, (1984), pp: 3088-3092.
  • Jine Cao, On stability of delayed cellular neural networks, Physics Letters A, 261(5-6), (1999), pp: 303-308.
  • R. Hush and Bill G. Horne, Progress in supervised Neural Networks, IEEE Signal Processing Magazine. January (1993).
  • Tino et al. Attractive Periodic Sets in DiscreteTime Recurrent Networks (with Emphasis on Fixed-Point Stability and Bifurcations in TwoNeuron Networks).Neural Computation (2001), 13(6), pp: 1379-1414.
  • X. Liao, K. Wong, Z. Wu, Bifurcation analysis on a two-neuron system with distributed delays, Physica D, 149, (2001), pp: 123-141.
  • X. Wang, Discrete-Time Dynamics of Coupled Quasi-Periodic and Chaotic Neural Network Oscillators, International Joint Conference on Neural Networks, 1992.
  • Y. A. Kuznetsov, Elements of Applied Bifurcation Theory, Springer-Verlag, New York Inc., Second Edition, 1998.