Application of Potts-Model Perceptron for Binary Patterns Identification (original) (raw)

Abstract

We suggest an effective algorithm based on q −state Potts model providing an exponential growth of network storage capacity M ~N 2_S_ + 1, where N is the dimension of the binary patterns and S is the free parameter of task. The algorithm allows us to identify a large number of highly distorted similar patterns. The negative influence of correlations of the patterns is suppressed by choosing a sufficiently large value of the parameter S. We show the efficiency of the algorithm by the example of a perceptron identifier, but it also can be used to increase the storage capacity of full connected systems of associative memory. Restrictions on S are discussed.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Perez-Vicente, C.J., Amit, D.J.: Optimized network for sparsely coded patterns. Journal of Physics A 22, 559–569 (1989)
    Article MathSciNet Google Scholar
  2. Palm, G., Sommer, F.T.: Information capacity in recurrent McCulloch-Pitts networks with sparsely coded memory states. Network 3, 1–10 (1992)
    Article Google Scholar
  3. Kryzhanovsky, B.V., Mikaelian, A.L.: An associative memory capable of recognizing strongly correlated patterns. Doklady Mathematics 67(3), 455–459 (2003)
    Google Scholar
  4. Kryzhanovsky, B.V., Mikaelian, A.L., Fonarev, A.B.: Vector neural network identifing many strongly distorted and correlated patterns. In: Int. conf on Information Optics and Photonics Technology, Photonics Asia-2004, Beijing-2004. Proc. of SPIE, vol. 5642, pp. 124–133 (2004)
    Google Scholar
  5. Kanter, I.: Potts-glass models of neural networks. Physical Review A 37(7), 2739–2742 (1988)
    Article MathSciNet Google Scholar
  6. Cook, J.: The mean-field theory of a Q-state neural network model. Journal of Physics A 22, 2000–2012 (1989)
    Article Google Scholar
  7. Vogt, H., Zippelius, A.: Invariant recognition in Potts glass neural networks. Journal of Physics A 25, 2209–2226 (1992)
    Article MATH MathSciNet Google Scholar
  8. Bolle, D., Dupont, P., Huyghebaert, J.: Thermodynamics properties of the q −state Potts-glass neural network. Phys. Rew. A 45, 4194–4197 (1992)
    Article Google Scholar
  9. Wu, F.Y.: The Potts model. Review of Modern Physics 54, 235–268 (1982)
    Article Google Scholar
  10. Nakamura, Y., Torii, K., Munaka, T.: Neural-network model composed of multidimensional spin neurons. Phys. Rev. E 51(2), 1538–1546 (1995)
    Article Google Scholar
  11. Kryzhanovsky, B.V., Mikaelyan, A.L.: On the Recognition Ability of a Neural Network on Neurons with Parametric Transformation of Frequencies. Doklady Mathematics 65(2), 286–288 (2002)
    Google Scholar
  12. Kryzhanovsky, B.V., Kryzhanovsky, V.M., Mikaelian, A.L., Fonarev, A.: Parametric dynamic neural network recognition power. Optical Memory&Neural Network 10(4), 211–218 (2001)
    Google Scholar
  13. Kryzhanovsky, B.V., Litinskii, L.B., Fonarev, A.: Parametrical neural network based on the four-wave mixing process. Nuclear Instuments and Methods in Physics Research, A 502(2-3), 517–519 (2003)
    Article Google Scholar
  14. Kryzhanovsky, B.V., Litinskii, L.B., Mikaelian, A.L.: Vector-neuron models of associative memory. In: Proc. of Int. Joint Conference on Neural Networks IJCNN 2004, Budapest-2004, pp. 909–1004 (2004)
    Google Scholar
  15. Kryzhanovsky, B.V., Kryzhanovsky, V.M., Fonarev, A.B.: Decorrelating Parametrical Neural Network. In: Proc. of IJCNN Montreal-2005, pp. 1023–1026 (2005)
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. Center of Optical Neural Technologies of Scientific Research Institute for System Analysis of Russian Academy of Sciences Email: iont.niisi@gmail.com, 44/2 Vavilov Street, 119333, Moscow, Russian Federation
    Vladimir Kryzhanovsky, Boris Kryzhanovsky & Anatoly Fonarev
  2. Department of Engineering and Science, CUNY City University of New York, 2800 Victory Blvd. SI, NY 10314
    Anatoly Fonarev

Authors

  1. Vladimir Kryzhanovsky
  2. Boris Kryzhanovsky
  3. Anatoly Fonarev

Editor information

Véra Kůrková Roman Neruda Jan Koutník

Rights and permissions

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kryzhanovsky, V., Kryzhanovsky, B., Fonarev, A. (2008). Application of Potts-Model Perceptron for Binary Patterns Identification. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9\_57

Download citation

Keywords

Publish with us