Skip to main content

On Conditions for Intermittent Search in Self-organizing Neural Networks

  • Conference paper
MICAI 2007: Advances in Artificial Intelligence (MICAI 2007)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 4827))

Included in the following conference series:

  • 1020 Accesses

Abstract

Self-organizing neural networks (SONN) driven by softmax weight renormalization are capable of finding high quality solutions of difficult assignment optimization problems. The renormalization is shaped by a temperature parameter - as the system cools down the assignment weights become increasingly crisp. It has been recently observed that there exists a critical temperature setting at which SONN is capable of powerful intermittent search through a multitude of high quality solutions represented as meta-stable states of SONN adaptation dynamics. The critical temperature depends on the problem size. It has been hypothesized that the intermittent search by SONN can occur only at temperatures close to the first (symmetry breaking) bifurcation temperature of the autonomous renormalization dynamics. In this paper we provide a rigorous support for the hypothesis by studying stability types of SONN renormalization equilibria.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Hopfield, J., Tank, D.: Neural computation of decisions in optimization problems. Biological Cybernetics 52, 141–152 (1985)

    MATH  MathSciNet  Google Scholar 

  2. Smith, K.: Neural networks for combinatorial optimization: a review of more than a decade of research. INFORMS Journal on Computing 11, 15–34 (1999)

    Article  MATH  MathSciNet  Google Scholar 

  3. Smith, K., Palaniswami, M., Krishnamoorthy, M.: Neural techniques for combinatorial optimization with applications. IEEE Transactions on Neural Networks 9, 1301–1318 (1998)

    Article  Google Scholar 

  4. Guerrero, F., Lozano, S., Smith, K., Canca, D., Kwok, T.: Manufacturing cell formation using a new self-organizing neural network. Computers & Industrial Engineering 42, 377–382 (2002)

    Article  Google Scholar 

  5. Kosowsky, J., Yuille, A.: The invisible hand algorithm: Solving the assignment problem with statistical physics. Neural Networks 7, 477–490 (1994)

    Article  MATH  Google Scholar 

  6. Kwok, T., Smith, K.: Optimization via intermittency with a self-organizing neural network. Neural Computation 17, 2454–2481 (2005)

    Article  MathSciNet  Google Scholar 

  7. Kwok, T., Smith, K.: Performance-enhancing bifurcations in a self-organising neural network. In: Mira, J.M., Álvarez, J.R. (eds.) IWANN 2003. LNCS, vol. 2686, pp. 390–397. Springer, Heidelberg (2003)

    Google Scholar 

  8. Kwok, T., Smith, K.: A noisy self-organizing neural network with bifurcation dynamics for combinatorial optimization. IEEE Transactions on Neural Networks 15, 84–88 (2004)

    Article  Google Scholar 

  9. Tiňo, P.: Equilibria of iterative softmax and critical temperatures for intermittent search in self-organizing neural networks. Neural Computation 19, 1056–1081 (2007)

    Article  MathSciNet  MATH  Google Scholar 

  10. Gold, S., Rangarajan, A.: Softmax to softassign: Neural network algorithms for combinatorial optimization. Journal of Artificial Neural Networks 2, 381–399 (1996)

    Google Scholar 

  11. Rangarajan, A.: Self-annealing and self-annihilation: unifying deterministic annealing and relaxation labeling. Pattern Recognition 33, 635–649 (2000)

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Alexander Gelbukh Ángel Fernando Kuri Morales

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Tiňo, P. (2007). On Conditions for Intermittent Search in Self-organizing Neural Networks. In: Gelbukh, A., Kuri Morales, Á.F. (eds) MICAI 2007: Advances in Artificial Intelligence. MICAI 2007. Lecture Notes in Computer Science(), vol 4827. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76631-5_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-76631-5_17

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-76630-8

  • Online ISBN: 978-3-540-76631-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics