Storage capacity of the exponential correlation associative memory

Neural Modeling (Biophysical and Structural Models)
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1606)


In this paper we analyze the pattern storage capacity of the exponential correlation associative memory(ECAM). This architecture was first studied by Chiueh and Goodman [3] who concluded that, under certain conditions on the input patterns, the memory has a storage capacity that was exponential in the length of the bit-patterns. A recent analysis by Pelillo and Hancock [9], using the Kanerva picture of recall, concluded that the storage capacity was limited by 2N−1/N2. Both of these analyses can be criticised on the basis that they overlook the role of initial bit-errors in the recall process and deal only with the capacity for perfect pattern recall. In other words, they fail to model the effect of presenting corrupted patterns to the memory. This can be expected to lead to a more pessimistic limit. Here we model the performance of the ECAM when presented with corrupted input patterns. Our model leads to an expression for the storage capacity of the ECAM both in terms of the length of the bit-patterns and the probability of bit-corruption in the original input patterns. These storage capacities agree closely with simulation. In addition, our results show that slightly superior performance can be obtained by selecting an optimal value of the exponential constant.


Exponential correlation associative memory storage capacity 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proc. Natl. Acad. Sci. USA, vol. 79, pp. 2554–2558, 1982.MathSciNetCrossRefGoogle Scholar
  2. 2.
    R. J. McEliece, E. C. Posner, E. R. Rodemich, and S. S. Venkatesh, “The capacity of the Hopfield associative memory,” IEEE Trans. Inform. Theory, vol. 33, pp. 461–482, 1987.MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    T. D. Chiueh and R. M. Goodman, “Recurrent correlation associative memories”, IEEE Trans. Neural Networks, vol. 2, pp. 275–284, 1991.CrossRefGoogle Scholar
  4. 4.
    T. D. Chiueh and R. M. Goodman, “VLSI implementation of a high-capacity neural network associative memory”, in D. S. Touretzky, Ed., Advances in Neural Information Processing Systems 2. San Mateo, CA: Morgan-Kaufmann, 1990, pp. 793–800.Google Scholar
  5. 5.
    C. C. Wang and H. S. Don, “An analysis of high-capacity discrete exponential BAM,” IEEE Trans. Neural Networks, vol. 6, pp. 492–496, 1995.CrossRefGoogle Scholar
  6. 6.
    C. C. Wang and J. P. Lee, “The decision-making properties of discrete multiple exponential bidirectional associative memories,” IEEE Trans. Neural Networks, vol. 6, pp. 993–999, 1995.CrossRefGoogle Scholar
  7. 7.
    T. D. Chiueh and H. K. Tsai, “Multi-valued associative memories based on recurrent networks,” IEEE Trans. Neural Networks, vol. 4, pp. 364–366, 1993.CrossRefGoogle Scholar
  8. 8.
    E.R. Hancock and J. Kittler, “Discrete Relaxation”, Pattern Recognition, 23, pp 711–733, 1990.CrossRefGoogle Scholar
  9. 9.
    E.R. Hancock and M. Pelillo, “A Bayesian Interpretation for the Exponential Correlation Associative Memory”, Pattern Recognition Letters, 19, pp. 149–159, 1998.CrossRefMATHGoogle Scholar
  10. 10.
    R. C. Wilson and E. R. Hancock, “Structural Matching by Discrete Relaxation”, IEEE Trans. Pattern Anal. Machine Intell., vol. 19, pp. 634–648, 1997.CrossRefGoogle Scholar
  11. 11.
    P. Kanerva, Sparse Distributed Memory. MIT Press, Cambridge, MA, 1988.MATHGoogle Scholar
  12. 12.
    D. Milun and D. Sher, “Improving sampled probability distributions for Markov random fields,” Pattern Recognition Letters. v 14 pp. 781–788 1993.CrossRefMATHGoogle Scholar
  13. 13.
    P. A. Chou, “The capacity of the Kanerva associative memory is exponential,” in D. Z. Anderson, Ed., Neural Information Processing Systems. New York, NY: American Institute of Physics, 1988, pp. 184–191.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of YorkYorkUK

Personalised recommendations