Skip to main content
SpringerLink
Log in

A vector model of associative memory with clipped synapses

  • Mathematical Theory of Pattern Recognition
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

The influence of a clipping procedure on the properties of vector associative memory is investigated. The analysis is performed for the particular case of a phase model of a parametric neural network with 2q-state neurons. The critical network size N c is found. It is shown that, for small network sizes (N < N c ), the clipping leads to an increase of the storage capacity and enhances the network ability to retrieve strongly distorted patterns. Clipping of bigger networks (N > N c ) leads to a deterioration of the recognition ability and reduces the storage capacity.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. I. Kanter, “Potts-Glass Models of Neural Networks,” Phys. Rev. A 37(7), 2739 (1988).

    Article  MathSciNet  Google Scholar 

  2. J. Cook, “The Mean-Field Theory of a Q-state Neural Network Model,” J. Phys. A 22, 2000 (1989).

    Article  Google Scholar 

  3. H. Vogt and A. Zippelius, “Invariant Recognition in Potts-Glass Neural Network,” J. Phys. A 25, 2209 (1992).

    Article  MATH  MathSciNet  Google Scholar 

  4. D. Bolle, P. Dupont, and J. van Mourik, “Stability Properties of Potts Neural Networks with Biased Pattern and Low Loading,” J. Phys. A 24, 1065 (1991).

    Article  MATH  Google Scholar 

  5. D. Bolle, P. Dupont, and J. Huyghebaert, “Thermodynamic Properties of the q-State Potts-Glass Neural Network,” Phys. Rev. A 45, 4194 (1992).

    Article  Google Scholar 

  6. F. Y. Wu, “The Potts Model,” Rev. Mod. Phys. 54, 235 (1982).

    Article  Google Scholar 

  7. B. V. Kryzhanovsky and A. L. Mikaelian, “On the Recognition Abilities of a Neural Network Using Neurons with Parametric Frequency Transformation,” Dokl. Akad. Nauk, Ser. Matem. Physics 383(3), 318 (2002).

    Google Scholar 

  8. B. V. Kryzhanovsky, V. M. Kryzhanovsky, A. L. Mikaelian, et al., “Parametric Dynamic Neural Network Recognition Power,” Optical Memory and Neural Networks 10(4), 211 (2001).

    Google Scholar 

  9. B. V. Kryzhanovsky and A. L. Mikaelian, “An Associative Memory Capable of Recognizing Strongly Correlated Patterns,” Dokl. Akad. Nauk, Ser. Informatics 390(1), 27 (2003).

    Google Scholar 

  10. B. Widrow and M. E. Hoff, Jr., “Adaptive Switching Circuits,” in 1960 IRE Western Electric Show and Convention Record, Part 4, 96 (1960).

  11. H. Sompolinsky, “Neural Network with Non-linear Synapses and Static Noise,” Phys. Rev. A 34 2571 (1986).

    Article  Google Scholar 

  12. J. L. van Hemmen, “Nonlinear Neural Network near Saturation,” Phys. Rev. A 36 1959 (1987).

    Article  Google Scholar 

  13. W. Kintzel and M. Opper, “Models of Neural Networks I,” in Physics of Neural Networks, Ed. by E. Domany, J. L. van Hemmen, and K. Schulten (Springer, Berlin, 1995) p. 170.

    Google Scholar 

  14. J. J. Hopfield, “Neural Networks and Physical Systems with Emergent Collective Computational Abilities”, Proc. Nat. Acad. Sci. USA 79, 2554 (1982).

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Center for Optical Neural Technologies, Scientific Research Institute for Systems Analysis, Russian Academy of Sciences, ul. Vavilova 44/2, Moscow, Russia

    B. V. Kryzhanovsky, D. I. Simkina & V. M. Kryzhanovsky

Authors
  1. B. V. Kryzhanovsky
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. I. Simkina
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. V. M. Kryzhanovsky
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to B. V. Kryzhanovsky.

Additional information

Boris Vladimirovich Kryzhanovsky was born in 1950 in Yasnaya Polyana in the Tula region of Russia and graduated (with an M.Sc.) from Yerevan State University in 1971. He received his Ph.D. (Optics) in 1981 and his D.Sc. (Laser Physics) in 1991. At the present time, he is the director of the Center for Optical Neural Technologies of the Scientific Research Institute for Systems Analysis of the Russian Academy of Sciences. His research interests include neural networks. He is a corresponding member of the Russian Academy of Sciences and the author of over 200 research publications.

Vladimir Mikhailovich Kryzhanovsky was born in 1984 in Kirovakan, Armenia and graduated (with an M.Sc.) from the Moscow Engineering Physics Institute in 2007. At the present time, he is a junior research assistant at the Center for Optical Neural Technologies of the Scientific Research Institute for Systems Analysis of the Russian Academy of Sciences. His research interests include Neural Networks, and he is the author of over 20 research publications.

Dina Igorevna Simkina was born 1981 in Buinaksk in Dagestan, Russia and graduated (with an M.Sc.) from Dagestan State University in 2003. At the present time, she is a junior research assistant at the Center for Optical Neural Technologies of the Scientific Research Institute for Systems Analysis of the Russian Academy of Sciences. Her research interests include neural networks, and she is the author of over 20 research publications.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kryzhanovsky, B.V., Simkina, D.I. & Kryzhanovsky, V.M. A vector model of associative memory with clipped synapses. Pattern Recognit. Image Anal. 19, 289–295 (2009). https://doi.org/10.1134/S1054661809020126

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661809020126

Keywords

Search

Navigation