Advertisement

Critical Temperatures for Intermittent Search in Self-Organizing Neural Networks

  • Peter Tiňo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4193)

Abstract

Kwok and Smith [1] recently proposed a new kind of optimization dynamics using self-organizing neural networks (SONN) driven by softmax weight renormalization. Such dynamics is capable of powerful intermittent search for high-quality solutions in difficult assignment optimization problems. However, the search is sensitive to temperature setting in the softmax renormalization step of the SONN algorithm. It has been hypothesized that the optimal temperature setting corresponds to symmetry breaking bifurcation of equilibria of the renormalization step, when viewed as an autonomous dynamical system called iterative softmax (ISM). We rigorously analyze equilibria of ISM by determining their number, position and stability types. Moreover, we offer analytical approximations to the critical symmetry breaking bifurcation temperatures that are in good agreement with those found by numerical investigations. So far the critical temperatures have been determined only via numerical simulations. On a set of N-queens problems for a wide range of problem sizes N, the analytically determined critical temperatures predict the optimal working temperatures for SONN intermittent search very well.

Keywords

Critical Temperature Bifurcation Point Stability Type Autonomous Dynamical System Symmetry Breaking Bifurcation 
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.
    Kwok, T., Smith, K.: Optimization via intermittency with a self-organizing neural network. Neural Computation 17, 2454–2481 (2005)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Hopfield, J.: Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Science, USA, 79, 2554–2558 (1982)Google Scholar
  3. 3.
    Smith, K.: Neural networks for combinatorial optimization: a review of more than a decade of research. INFORMS Journal on Computing 11, 15–34 (1999)MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Smith, K.: Solving the generalized quadratic assignment problem using a self-organizing process. In: Proceedings of the IEEE Int. Conf. on Neural Networks, vol. 4, pp. 1876–1879 (1995)Google Scholar
  5. 5.
    Smith, K., Palaniswami, M., Krishnamoorthy, M.: Neural techniques for combinatorial optimization with applications. IEEE Transactions on Neural Networks 9, 1301–1318 (1998)CrossRefGoogle Scholar
  6. 6.
    Kwok, T., Smith, K.: Performance-enhancing bifurcations in a self-organising neural network. In: Mira, J., Álvarez, J.R. (eds.) IWANN 2003. LNCS, vol. 2686, pp. 390–397. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  7. 7.
    Langton, C.: Computation at the edge of chaos: Phase transitions and emergent computation. Physica D 42, 12–37 (1990)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Tiňo, P.: Equilibria of iterative softmax and critical temperatures for intermittent search in self-organizing neural networks. Technical Report CSRP-06-07, University of Birmingham, School of Computer Science (2006), http://www.cs.bham.ac.uk/~pxt/PAPERS/tino.tr06.pdf

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Peter Tiňo
    • 1
  1. 1.School Of Computer ScienceUniversity of Of BirminghamBirminghamUK

Personalised recommendations