Skip to main content

Theoretical Study on the Capacity of Associative Memory with Multiple Reference Points

  • Conference paper
Bio-inspired Modeling of Cognitive Tasks (IWINAC 2007)

Abstract

An extension to Hopfield’s model of associative memory is studied in the present work. In particular, this paper is focused in giving solutions to the two main problems present in the model: the apparition of spurious patterns in the learning phase (implying the well-known and undesirable effect of storing the opposite pattern) and the problem of its reduced capacity (the probability of error in the retrieving phase increases as the number of stored patterns grows). In this work, a method to avoid spurious patterns is presented and studied, and an explanation to the previously mentioned effect is given. Another novel technique to increase the capacity of a network is proposed here, based on the idea of using several reference points when storing patterns. It is studied in depth, and an explicit formula for the capacity of the network is provided. This formula shows the linear dependence of the capacity of the new model on the number of reference points, implying the increase of the capacity in this model.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Hopfield, J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. U S A 79, 2254–2558 (1982)

    Article  MathSciNet  Google Scholar 

  2. Hebb, D.O.: The Organization of Behavior. Wiley, Chichester (1949)

    Google Scholar 

  3. Parisi, G.: Asymmetric neural networks and the process of learning. J. Phys. A: Math. and Gen. 19, L675–L680 (1986)

    Article  MathSciNet  Google Scholar 

  4. Hertz, J.A., Grinstein, G., Solla, S.A.: In: Heidelberg Colloquium on Glassy Dynamics, Springer, Heidelberg (1987)

    Google Scholar 

  5. Treves, A., Amit, D.J.: Metastable states in asymmetrically diluted hopfield networks. J. Phys A: Math. and Gen. 21, 3155–3169 (1988)

    Article  MathSciNet  MATH  Google Scholar 

  6. Singh, M.P., Chengxiang, Z., Dasgupta, C.: Analytic study of the effects of synaptic asymmetry. Phys. Rev. E 52, 5261–5272 (1995)

    Article  Google Scholar 

  7. Athithan, G., Dasgupta, C.: On the problem of spurious patterns in neural associative models. IEEE Transactions on Neural Networks 8, 1483–1491 (1997)

    Article  Google Scholar 

  8. Crick, F., Mitchinson, G.: The function of dream sleep. Nature 304, 111–114 (1983)

    Article  Google Scholar 

  9. van Hemmen, J.L., Kuhn, R.: Collective Phenomena in Neural Networks. Springer, Heidelberg (1991)

    Google Scholar 

  10. McEliece, R.J., Posner, E.C., Rodemich, E.R., Venkatesh, S.S.: The capacity of the hopfield associative memory. IEEE Transactions on Information Theory 33, 461–482 (1987)

    Article  MathSciNet  MATH  Google Scholar 

  11. Ho, C.Y., Sasase, I., Mori, S.: On the capacity of the hopfield associative memory. In: Proceedings of IJCNN, pp. II196–II201 (1992)

    Google Scholar 

  12. Kuh, A., Dickinson, B.W.: Information capacity of associative memory. IEEE Transactions on Information Theory 35, 59–68 (1989)

    Article  MathSciNet  MATH  Google Scholar 

  13. Mérida-Casermeiro, E., Muñoz Pérez, J.: Mrem: An associative autonomous recurrent network. Journal of Intelligent and Fuzzy Systems 12, 163–173 (2002)

    MATH  Google Scholar 

  14. Mérida-Casermeiro, E., Galán-Marín, G., Muñoz Pérez, J.: An efficient multivalued hopfield network for the travelling salesman problem. Neural Processing Letters 14, 203–216 (2001)

    Article  MATH  Google Scholar 

  15. Erdem, M.H., Ozturk, Y.: A new family of multivalued networks. Neural Networks 9, 979–989 (1996)

    Article  Google Scholar 

  16. Ozturk, Y., Abut, H.: System of associative relationships, soar (1997)

    Google Scholar 

  17. Mérida-Casermeiro, E., Muñoz Pérez, J., Domínguez-Merino, E.: An n-parallel multivalued network: Applications to the travelling salesman problem. In: Mira, J., Álvarez, J.R. (eds.) IWANN 2003. LNCS, vol. 2686, pp. 406–413. Springer, Heidelberg (2003)

    Chapter  Google Scholar 

  18. López-Rodríguez, D., Mérida-Casermeiro, E., Ortiz-de Lazcano-Lobato, J.M.: Hopfield network as associative memory with multiple reference points. In: Ardil, C. (ed.) International Enformatika Conference, pp. 62–67 (2005)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

José Mira José R. Álvarez

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer Berlin Heidelberg

About this paper

Cite this paper

Mérida-Casermeiro, E., López-Rodríguez, D., Galán-Marín, G., Ortiz-de-Lazcano-Lobato, J.M. (2007). Theoretical Study on the Capacity of Associative Memory with Multiple Reference Points. In: Mira, J., Álvarez, J.R. (eds) Bio-inspired Modeling of Cognitive Tasks. IWINAC 2007. Lecture Notes in Computer Science, vol 4527. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73053-8_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-73053-8_29

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-73052-1

  • Online ISBN: 978-3-540-73053-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics