Advertisement

Solving the CLM Problem by Discrete-Time Linear Threshold Recurrent Neural Networks

  • Lei Zhang
  • Pheng Ann Heng
  • Zhang Yi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5768)

Abstract

The competitive layer model (CLM) can be described by the optimization problem that is formulated with the CLM energy function. The minimum points of CLM energy function can be achieved by running some proper recurrent neural networks. In other words, the CLM can be implemented by the recurrent neural networks. This paper proposes the discrete-time linear threshold recurrent networks to solve the CLM problem. The conditions for the stable attractors of the networks are obtained, which just correspond to the conditions of the minimum points of CLM energy function established in the literature before. Therefore, the proposed network can be used to implement the CLM.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ritter, H.: A Spatial Approach for Feature Linking. In: Proc. Int. Neural Networks Conf., Paris, vol. 2, pp. 898–901 (1990)Google Scholar
  2. 2.
    Von der Malsburg, C.: Binding in Models of Perception and Brain Function. Current Opinion in Neurobiology 5, 520–526 (1995)CrossRefGoogle Scholar
  3. 3.
    Wersing, H., Steil, J.J., Ritter, H.: A Competitive Layer Model for Feature Binding and Sensory Segmentation. Neural Computation 13, 357–387 (2001)CrossRefzbMATHGoogle Scholar
  4. 4.
    Yi, Z.: Foundations of Implementing the Competitive Layer Model by Lotka-Volterra Recurrent Neural Networks. Conditionally Accepted by IEEE Trans. Neural Networks (2009)Google Scholar
  5. 5.
    Zhang, L., Yi, Z., Yu, J.: Multiperiodicity and Attractivity of Delayed Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions. IEEE Trans. Neural Networks 19, 158–167 (2008)CrossRefGoogle Scholar
  6. 6.
    Yu, J., Yi, Z., Zhang, L.: Representations of Continuous Attractors of Recurrent Neural Networks. IEEE Trans. Neural Networks 20, 368–372 (2009)CrossRefGoogle Scholar
  7. 7.
    Yi, Z., Tan, K.K.: Multistability Analysis of Discrete Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions. IEEE Trans. Neural Networks 15, 329–336 (2004)CrossRefGoogle Scholar
  8. 8.
    Goldberg, J.L.: Matrix Theory with Applications. McGraw-Hill, New York (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Lei Zhang
    • 1
  • Pheng Ann Heng
    • 1
    • 2
  • Zhang Yi
    • 3
  1. 1.Department of Computer Science and EngineeringThe Chinese University of Hong Kong,ShatinHong Kong
  2. 2.School of Computer Science and EngineeringUniversity of Electronic Science and TechnologyChengduP.R. China
  3. 3.Machine Intelligence Laboratory, School of Computer ScienceSichuan UniversityChengduP.R. China

Personalised recommendations