Advertisement

Fascinating Rhythms by Chaotic Hopfield Networks

  • Colin Molter
  • Hugues Bersini
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2801)

Abstract

This papers aims to introduce a new way to store inputs in the network. By this way, it appears that the spontaneous dynamics of the network will increase in complexity by increasing the size of the learning set. This experimental work might give additional support to the Skarda and Freeman strong intuition that chaos should play an important role in the storage and the search capacities of our brains. An analysis of the type of chaos exploited to code these inputs will be related with the “frustrated chaos” described in previous papers. A live demonstration can be shown where rhythms and melodies associated with the dynamics can be heard.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Werbos, P.: Backpropagation through time: what it does and how to do it. Proceedings of the IEEE 78(10), 1550–1560 (1990)CrossRefGoogle Scholar
  2. 2.
    Feldkamp, L., Prokhorov, D., Eagen, C., Yuan, F.: Enhanced multi-stream kalman filter training for recurrent networks. Nonlinear modeling: advanced black-box techniques, 29–53 (1998)Google Scholar
  3. 3.
    Jaeger, H.: The “echo state” approach to analyzing and training recurrent neural networks. GMD - German National Research Institute for Computer Science GMD Report 148 (2001)Google Scholar
  4. 4.
    Orponen, P., Šíma, J.: On the computational complexity of binary and analog symetric Hopfields Nets. Neural Computation 12, 2965–2989 (2000)CrossRefGoogle Scholar
  5. 5.
    Skarda, C., Freeman, W.: How brains make chaos in order to make sense of the world. Behavioral and Brain Sciences 10, 161–195 (1987)CrossRefGoogle Scholar
  6. 6.
    Babloyantz, A.: Lourenço: Computation with chaos: A paradigm for cortical activity. Proceedings of National Academy of Sciences 91, 9027–9031 (1994)CrossRefGoogle Scholar
  7. 7.
    Freeman, W.: Simulation of chaotic eeg patterns with a dynamic model of the olfactory system. Biological Cybernetics 56, 139–150 (1987)CrossRefGoogle Scholar
  8. 8.
    Gelder, T.V.: The dynamical hypothesis in cognitive science. Behavioral and Brain Sciences (1997)Google Scholar
  9. 9.
    Gray, C., Köning, P., Engel, A., Singer, W.: Nature, vol. 338, pp. 334–337 (1989)Google Scholar
  10. 10.
    Ishii, S., Fukumizuet, K., Watanabe, S.: A network of chaotic elements for information processing. Neural Networks 9, 25–40 (1996)CrossRefGoogle Scholar
  11. 11.
    Kozma, R., Freeman, W.: Chaotic resonance - methods and applications for robust classification of noisy and variable pattern. International Journal of Bifurcation and Chaos 11, 1607–1629 (2001)CrossRefGoogle Scholar
  12. 12.
    Pasemann, F.: Neuromodules: A dynamical systems approach to brain modelling. Supercomputing in brain Research, 331–348, World Scientific, Singapore (1995)Google Scholar
  13. 13.
    Tsuda, I.: Towards an interpretation of dynamic neural activity in terms of chaotic dynamical systems. Behavioral and Brain Sciences 24 (2001)Google Scholar
  14. 14.
    Rodriguez, E., Jamel, B., Lachaux, J., Lutz, A., Martinerie, J., Reunault, B., Varela, F.: She’s got bette davis eyes: Multi-band brain synchrony during a complex visual task. Nature 397, 430–433 (1999)CrossRefGoogle Scholar
  15. 15.
    Bersini, H., Calenbuhr, V.: Frustrated chaos in biological networks. J. theor. Biol. 177, 199–213 (1997)Google Scholar
  16. 16.
    Bersini, H.: The frustrated and Compositionnal Nature of Chaos in Small Hopfield Networks. Neural Networks 11, 1017–1025 (1998)CrossRefGoogle Scholar
  17. 17.
    Pomeau, Y., Manneville, P.: Intermittent transitions to turbulence in dissipative dynamical systems. Comm. Math. Phys. 74, 189–197 (1980)CrossRefMathSciNetGoogle Scholar
  18. 18.
    Ott, E.: Chaos in Dynamical Systems. Cambridge University Press, Cambridge (1993)zbMATHGoogle Scholar
  19. 19.
    Kentridge, R.: Computation, chaos and non-deterministic symbolic computation: The chinese room problem solved? Psycoloquy (12) 17Google Scholar
  20. 20.
    Hao, B.: Symbolic dynamics and characterization of complexity. Physica D 51, 161–176 (1991)zbMATHCrossRefMathSciNetGoogle Scholar
  21. 21.
    Dechert, W., Sprott, J., Albers, D.: On the probability of Chaos in large Dynamical Systems: A monte carlo study. Journal of Economic Dynamics & Control 23, 1197–1206 (1999)CrossRefGoogle Scholar
  22. 22.
    Kelso, J., Case, P., Holroyd, T., Horvath, E., Raçzaszek, J., Tuller, B., Ding, M.: Multistability and metastability in perceptual and brain dynamics. In: Ambiguity in Mind and Nature: multistable cognitive phenomena. Springer Series in Synergetic, vol. 64 (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Colin Molter
    • 1
  • Hugues Bersini
    • 1
  1. 1.Laboratory of Artificial IntelligenceUniversity of BrusselsBrusselsBelgium

Personalised recommendations