FEEDBACK CONTROL TAMES DISORDER IN ATTRACTOR NEURAL NETWORKS

Maria Pietronilla Penna, Anna Montesanto, Eliano Pessa

Abstract

Typical attractor neural networks (ANN) used to model associative memories behave like disordered systems, as the asymptotic state of their dynamics depends in a crucial (and often unpredictable) way on the chosen initial state. In this paper we suggest that this circumstance occurs only when we deal with such ANN as isolated systems. If we introduce a suitable control, coming from the interaction with a reactive external environment, then the disordered nature of ANN dynamics can be reduced, or even disappear. To support this claim we resort to a simple example based on a version of Hopfield autoassociative memory model interacting with an external environment which modifies the network weights as a function of the equilibrium state coming from retrieval dynamics.

References

  1. Amit, D.J., 1989. Modeling Brain Function. The world of Attractor Neural Networks. Cambridge University Press, Cambridge, UK.
  2. Becker, S., Lim, J., 2003. A computational model of prefrontal control in free recall: Strategic memory use in the California verbal learning task. Journal of Cognitive Neuroscience, 15, 821-832.
  3. Bovier, A., 2006. Statistical Mechanics of Disordered Systems. A Mathematical Perspective, Cambridge University Press. Cambridge, UK.
  4. Buchleiter, A., Hornberger, K., (Eds.) 2002. Coherent evolution in noisy environments, Springer. Berlin.
  5. Dotsenko, V., 1995. An introduction to the theory of spin glasses and neural networks, World Scientific. Singapore.
  6. Engel, A., Van den Broeck, C., 2001. Statistical mechanics of learning, Cambridge University Press. Cambridge, UK.
  7. He, G., Cao, Z., Zhu, P., Ogura, H., 2003. Controlling chaos in a chaotic neural network. Neural Networks, 16, 1195-1200.
  8. Hua, C., Guan, X., 2004. Adaptive control for chaotic systems. Chaos, Solitons and Fractals, 22, 55-60.
  9. Kamp, Y., Hasler, M., 1990. Recursive neural networks for associative memory, Wiley. Chichester, UK.
  10. Kohonen, T., 1995. Self-Organizing Maps, Springer. Berlin.
  11. Kushibe, M., Liu, Y., Ohtsubo, J., 1996. Associative memory with spatiotemporal chaos control. Physical Review E, 53, 4502-4508.
  12. Medsker, L.R., Jain, L.C., (Eds.) 2000. Recurrent neural networks. Design and applications, CRC Press. Boca Raton, FL.
  13. Miyashita, Y., 2004. Cognitive memory: Cellular and network machineries and their top-down control. Science, 306, 435-440.
  14. Olshauen, B.A., Field, D.J., 2004. Sparse coding of sensory inputs. Current Opinion in Neurobiology, 14, 481-487.
  15. Peretto, P., 1992. An introduction to the modeling of neural networks, Cambridge University Press. Cambridge, UK.
  16. Rolls, E.T., Tovee, M.J., 1995. Sparseness of the neuronal representation of stimuli in the primate temporal visual cortex. Journal of Neurophysiology, 73, 713-726.
  17. Schlosshauer, M., 2007. Decoherence and the Quantumto-classical transition, Springer. Berlin.
  18. Tang, H., Tan, K.C., Yi, Z., 2007. Neural networks: Computational models and applications, Springer. Berlin.
  19. Willmore, B., Tolhurst, D., 2001. Characterising the sparseness of neural codes. Network: Computation in Neural Systems, 12, 255-270.
Download


Paper Citation


in Harvard Style

Pietronilla Penna M., Montesanto A. and Pessa E. (2009). FEEDBACK CONTROL TAMES DISORDER IN ATTRACTOR NEURAL NETWORKS . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 446-451. DOI: 10.5220/0002318604460451


in Bibtex Style

@conference{icnc09,
author={Maria Pietronilla Penna and Anna Montesanto and Eliano Pessa},
title={FEEDBACK CONTROL TAMES DISORDER IN ATTRACTOR NEURAL NETWORKS},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={446-451},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002318604460451},
isbn={978-989-674-014-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - FEEDBACK CONTROL TAMES DISORDER IN ATTRACTOR NEURAL NETWORKS
SN - 978-989-674-014-6
AU - Pietronilla Penna M.
AU - Montesanto A.
AU - Pessa E.
PY - 2009
SP - 446
EP - 451
DO - 10.5220/0002318604460451