Advertisement

Domain Dynamics in Optimization Tasks

  • Boris Kryzhanovsky
  • Bashir Magomedov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4029)

Abstract

A new type of dynamics of Hopfiled model – the domain dynamics – is proposed for using in optimization tasks. It is shown that this kind of dynamic allows one to find more deep minima of the energy than the standard asynchronous dynamics. It is important that the number of calculation does not rise when we replace standard spin dynamics by the domain one.

Keywords

Spin Dynamic Optimization Task Deep Minimum Domain Network Domain Dynamic 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hopfield, J.: Neural Networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. Sci. USA 79, 2554–2558 (1982)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Hebb, D.: The Organization of Behavior. Wiley, New York (1949)Google Scholar
  3. 3.
    Palm, G., Sommer, F.: Information capacity in recurrent McCulloch-Pitts networks with sparsely coded memory states. Network 3, 177–186 (1992)MATHCrossRefGoogle Scholar
  4. 4.
    Abu-Mostafa, Y.S., St. Jacques, J.: Information capacity of the Hopfield model. IEEE Transactions on Information Theory 31(4), 461–464 (1985)MATHCrossRefGoogle Scholar
  5. 5.
    Cohen, M.A., Grossberg, S.G.: Absolute stability of global pattern formation and parallel memory storage by compatitive neural networks. IEEE Transactions on Systems, Man and Cybernetics 13, 815–826 (1983)MATHMathSciNetGoogle Scholar
  6. 6.
    Grossberg, S.: The adapptive brain, vol. 1,2. North-Holland, Amsterdam (1987)Google Scholar
  7. 7.
    Amit, D.J., Gutfreund, H., Sompolinsky, H.: Statistical mechanics of neural networks near saturation. Annal of Physics 173, 30–67 (1987)CrossRefGoogle Scholar
  8. 8.
    Kinzel, W.: Learning and pattern recognition in spin glass models. 2 Physik B 60, 205–213 (1985)MathSciNetGoogle Scholar
  9. 9.
    Kryzhanovsky, B.V., Mikaelian, A.L.: An associative memory capable of recognizing strongly correlated patterns. Doklady Mathematics 67(3), 455–459 (2003)Google Scholar
  10. 10.
    Kryzhanovsky, B., Magomedov, B., Mikaelian, A.: Domain Model of a Neural Network. Doklady Mathematics 71(2), 310–314 (2005)Google Scholar
  11. 11.
    Kryzhanovsky, B.V., Magomedov, B.M., Mikaelyan, A.L.: A Relation between the Depth of a Local Minimum and the Probability of Its Detection in the Generalized Hopfield Model. Doklady Mathematics 72(3), 986–991 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Boris Kryzhanovsky
    • 1
  • Bashir Magomedov
    • 1
  1. 1.Institute for optical-neural technologies RASMoscowRussia

Personalised recommendations