Advertisement

Neural Processing Letters

, Volume 4, Issue 1, pp 17–27 | Cite as

An energy function for the random neural network

  • Jose Aguilar C.
Article

Abstract

Since Hopfield's seminal work on energy functions for neural networks and their consequence for the approximate solution of optimization problems, much attention has been devoted to neural heuristics for combinatorial optimization. These heuristics are often very time-consuming because of the need for randomization or Monte Carlo simulation during the search for solutions. In this paper, we propose a general energy function for a new neural model, the random neural model of Gelenbe. This model proposes a scheme of interaction between the neurons and not a dynamic equation of the system. Then, we apply this general energy function to different optimization problems.

Key words

energy function optimization problems random neural network 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J.Hopfield and D.Tank. “Neural computation of decisions in optimization problem”, Biological Cybernetics, Vol. 52, pp. 141–152, 1985.Google Scholar
  2. 2.
    E.Gelenbe. “Random neural networks with positive and negative signals and product form solution”, Neural Computation, Vol. 1, No. 4, pp. 502–510, 1989.Google Scholar
  3. 3.
    E.Gelenbe. “Stable random neural networks”, Neural Computation, Vol. 2, No. 2, pp. 239–247, 1990.Google Scholar
  4. 4.
    E. Gelenbe. “Theory of the random neural network model”, in E. Gelenbe (ed) Neural Networks: Advances and Applications, North-Holland, pp. 1–20, 1991.Google Scholar
  5. 5.
    E. Gelenbe and F. Batty. “Application of the random neural network model to minimum graph covering”, in E. Gelenbe (ed) Neural Networks: Advances and Applications 2, North Holland: pp. 36–45, 1992.Google Scholar
  6. 6.
    J. Aguilar. “L'allocation de tâches, l'équilibrage de la charge et l'optimisation combinatoire”, PhD thesis, UFR Mathematique et Informatique, Rene Descartes University, France, 1995.Google Scholar
  7. 7.
    E.Gelenbe. “Learning in the recurrent Random Neural Network”, Neural Computation, Vol. 5, No. 5, pp. 154–164, 1993.Google Scholar
  8. 8.
    J.Aguilar. “An approach for combinatorial optimization problem based on learning in the recurrent random neural network”, Proceedings of the World Congress on Neural Networks, pp. 420–424, International Neural Network Society: San Diego, CA, USA, July 1994.Google Scholar
  9. 9.
    J.Aguilar. “Evolutionary Learning on Recurrent Random Neural Network”, Proceedings of the World Congress on Neural Networks, pp. 232–236, International Neural Network Society: Washington, DC, USA, July 1995.Google Scholar

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • Jose Aguilar C.
    • 1
  1. 1.Dpto. de Computación, Facultad de IngenieríaUniversidad de los AndesMéridaVenezuela

Personalised recommendations