Skip to main content
SpringerLink
Log in

A comparative study of two learning rules for associative memory

  • Research Articles
  • Published:
Pramana Aims and scope Submit manuscript

Abstract

This paper addresses itself to a practical problem encountered in using iterative learning rules for associative memory models. The performance of a learning rule based on linear programming which overcomes this problem is compared with that of a representative iterative rule by numerical simulation. Results indicate superior performance by the linear programming rule. An algorithm for computing radii of maximal hyperspheres around patterns in the state space of a model is presented. Fractional volumes of basins of attractions are computed for the representative iterative rule as well as the linear programming rule. With the radii of maximal hyperspheres as weight factors for corresponding patterns to be stored, the linear programming rule gives rise to the maximal utilisation of the state space.

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. W S McCulloch and W A Pitts,Bull. Math. Biophys. 5, 115 (1943)

    Article  MATH  MathSciNet  Google Scholar 

  2. J J Hopfield,Proc. Natl. Acad. Sci. USA 79, 2554 (1982)

    Article  ADS  MathSciNet  Google Scholar 

  3. D O Hebb,Organisation of behaviour (New York: Wiley, 1949)

    Google Scholar 

  4. D J Amit, H Gutfreund and H Sompolinsky,Ann. Phys. NY 173, 30 (1987)

    Article  ADS  Google Scholar 

  5. L Personnaz, L Guyon and G Dreyfus,J. Phys. Lett. 46, L359 (1985)

  6. D J Willshaw, O P Buneman and H C Languet-Higgins,Nature (London) 222, 960 (1969)

    Article  ADS  Google Scholar 

  7. E Domany, J L van Hemmen and K Shulten (eds),Models of neural networks (Berlin, Heidelberg: Springer Verlag, 1991)

    MATH  Google Scholar 

  8. E Gardner,Europhys. Lett. 4, 481 (1987)

    Article  ADS  Google Scholar 

  9. G Poeppel and U Krey,Europhys. Lett. 4, 979 (1988)

    Article  ADS  Google Scholar 

  10. S Diederich and M Opper,Phys. Rev. Lett. 58, 949 (1987)

    Article  ADS  MathSciNet  Google Scholar 

  11. W Krauth and M Mezard,J. Phys. A20, L745 (1987)

  12. B Forrest,J. Phys. A21, 245 (1988)

    ADS  MathSciNet  Google Scholar 

  13. L F Abbott and T B Kepler,J. Phys. A22, L711 (1989)

  14. J K Anlauf and M Biehl,Europhys. Lett. 10, 687 (1989)

    Article  ADS  Google Scholar 

  15. E Gardner,J. Phys. A21, 257 (1988)

    ADS  Google Scholar 

  16. M Griniasty and H Gutfreund,J. Phys. A24, 715 (1991)

    ADS  Google Scholar 

  17. W H Press, S A Teukolsky, W T Vellerling and B P Flannery,Numerical recipes in C (Cambridge University Press, 1992)

Download references

Author information

Authors and Affiliations

  1. Advanced Numerical Research and Analysis Group, P.O. Kanchanbagh, 500 258, Hyderabad, India

    G Athithan

Authors
  1. G Athithan
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Athithan, G. A comparative study of two learning rules for associative memory. Pramana - J Phys 45, 569–582 (1995). https://doi.org/10.1007/BF02848180

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02848180

Keywords

PACS Nos

Search

Navigation