Synthesis of adaptive memories with neural networks

  • Francisco J. Lopez Aligué
  • M. Isabel Acevedo Sotoca
  • M. Angel Jaramillo Moran
Neural Network Architectures And Algorithms
Part of the Lecture Notes in Computer Science book series (LNCS, volume 540)


The general formulation of bidirectional associative memories presents certain difficulties when the associations of pairs of patterns do not suppose a local energy minimun. To avoid these problems, the present paper describes an adaptive scheme which al lows the correlation matrix to be modified so as to reach the energy minimun while at the same time identifying the input patterns. The strategy described here allows the adaptation of the matrix to be performed for each external input, so that it can henceforth be described as a supervised type of training scheme. A consequence is its synthesis by means of neural networks with both the BAM and the adaptive mechanism itself integrated in distinct layers, allowing either of them to be changed without altering the other.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

VI. References

  1. [1]
    S. Amari, "Learning patterns and pattern sequences by self-organizing nets of threshold elements", IEEE Trans. on Computers., vol. C-21, 1972, pp. 1197–1206.Google Scholar
  2. [2]
    T. Kohonen, Associative Memory: A System-Theoretical Approach, Springer-Verlag, 1977.Google Scholar
  3. [3]
    B. Kosko, "Constructing an associative memory", Byte, vol. 12. No.10, pp. 137–144, Sept. 1987.Google Scholar
  4. [4]
    B. Kosko, "Bidirectional associative memories", Trans. on Syst. Man, Cybernetics., vol. 18, No. 1, pp. 49–60, Jan/Feb. 1988.Google Scholar
  5. [5]
    J.J. Hopfield, "Neurons with graded response have collective computational properties like those of two-state neurons”, Proc. of the Nat. Acad. of Sciences, U.S.A. 81, May 1984, pp. 3080–92.Google Scholar
  6. [6]
    Y. Abu-Mostafa, and J.M. St. Jacques, "Information Capacity of the Hopfield Model", IEEE Trans. on Information Theory, vol. 31, No. 4, pp. 461–464, July 1985.Google Scholar
  7. [7]
    R.J. McEliece, E.C. Posner, E.R. Rodemich, and S.S. Venkatesh, "The Capacity of the Hopfield Associative Memory", IEEE Trans. on Information Theory, vol. 33, No. 4, pp. 461–482, July 1987.Google Scholar
  8. [8]
    X. Xu, and W.T. Tsai, "Constructing Associative Memories using Neural Networks", neural Networks, vol. 3, No. 3, pp. 301–309, 1990.Google Scholar
  9. [9]
    S. Amari, and M. Kenjiro, "Statistical Neurodynamics of Associative Memory", Neural Networks, vol. 1, No. 1, pp. 63–73, 1988.Google Scholar
  10. [10]
    Y.F. Wang, J.B. Cruz, J.H. Mulligan, Jr., "Two Coding Strategies for Bidirectional Associative Memory", IEEE Trans. on Neural Networks, vol. 1, No. 1, pp. 81–92. March 1990.Google Scholar
  11. [11]
    — —.: "On Multiple Training for Bidirectional Associative Memory". IEEE Trans. on Neural Networks. Vol.1, No.3., pp. 275–276. Sept.1990Google Scholar
  12. [12]
    P.K. Simpson, "Higher-Ordered and Intraconnected Bidirectional Associative Memories", IEEE Trans. on Systems, Man and Cybernetics, vol. 20, No. 3, pp. 637–653, May/June 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • Francisco J. Lopez Aligué
    • 1
  • M. Isabel Acevedo Sotoca
    • 1
  • M. Angel Jaramillo Moran
    • 1
  1. 1.Departamento de Electrónica e Ingeniería ElectromecánicaUniversidad de ExtremaduraBadajozSpain

Personalised recommendations