Advertisement

Improved Pseudo-Relaxation Learning Algorithm for Robust Bidirectional Associative Memory

  • K. Hasegawa
  • M. Hattori
Conference paper

Abstract

In this paper, we propose Improved Pseudo-Relaxation Learning Algorithm for Bidirectional Associative Memory (IPRLAB). Since the proposed IPRLAB is based on the conventional PRLAB, it can guarantee the recall of all training pairs and has high storage capacity. Furthermore, the proposed IPRLAB can much improve the noise reduction effect of the BAM and contribute to construct a robust memory. A number of computer simulation results show the effectiveness of the proposed learning algorithm.

Keywords

Training Data Solution Space Linear Inequality Recall Rate Direction Cosine 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Nakano, K.: Association — a model of associative memory. IEEE Trans. Syst. Man. Cybern., SMC-2, no.1, pp.380–388 (1972).CrossRefGoogle Scholar
  2. [2]
    Hopfield, J.J.: Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proc. of National Academy Sciences USA, 79, pp.2554–2558 (1982).MathSciNetCrossRefGoogle Scholar
  3. [3]
    Hirai, Y.: A model of human associative processor (HASP). IEEE Trans. Syst. Man. Cybern., SMC-13, no.5, pp.851–857 (1983).MathSciNetCrossRefGoogle Scholar
  4. [4]
    Kosko, B.: Bidirectional Associative Memories. IEEE Trans. Syst. Man. Cybern., 18, no.1, pp.49–60 (1988).MathSciNetCrossRefGoogle Scholar
  5. [5]
    Hagiwara, M.: Multidirectional Associative Memory. Proc. of IJCNN′90, Washington, D.C., 1, pp.3–6 (1990).Google Scholar
  6. [6]
    Morita, M., Yoshizawa, S. and Nakano, K.: Analysis and Improvement of the Dynamics of Autocorrelation Associative Memory. IEICE Japan, J73-D-II, no.2, pp.232–242 (1990).Google Scholar
  7. [7]
    Wang, Y.F., Cruz, Jr., J.B and Mulligan, Jr., J.H.: Two Coding Strategies for Bidirectional Associative Memory. IEEE Trans. Neural Networks, 1, no. 1, pp.81–91 (1990).CrossRefGoogle Scholar
  8. [8]
    Wang, Y.F., Cruz, Jr., J.B and Mulligan, Jr., J.H.: Guaranteed Recall of All Training Pairs for Bidirectional Associative Memory. IEEE Trans. Neural Networks, 2, no.6, pp.559–567 (1991).CrossRefGoogle Scholar
  9. [9]
    Oh, H. and Kothari, S.C.: Adaptation of the Relaxation Method for Learning in Bidirectional Associative Memory. IEEE Trans. Neural Networks, 5, no.4, pp.576–583 (1994).CrossRefGoogle Scholar
  10. [10]
    Hattori, M., Hagiwara, M. and Nakagawa, M.: Quick Learning for Bidirectional Associative Memory. IEICE Japan, E77-D, no.4, pp.385–392 (1994).Google Scholar
  11. [11]
    Hattori, M. and Hagiwara, M.: Intersection Learning for Bidirectional Associative Memory. Proc. of ICNN′96, 1, pp.555–560 (1996).Google Scholar
  12. [12]
    Hattori, M. and Hagiwara, M.: Episodic Associative Memory. Neurocomputing, 12, pp. 1–18(1996).MATHCrossRefGoogle Scholar
  13. [13]
    Hattori, M. and Hagiwara, M.: Neural Associative Memory for Intelligent Information Processing. Proc. of KES′98, Adelaide, 2, pp.377–386 (1998).Google Scholar
  14. [14]
    Hattori, M. and Hagiwara, M.: Multimodule Associative Memory for Many-to-Many Associations. Neurocomputing, 19, pp. 99–119 (1998).CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 1999

Authors and Affiliations

  • K. Hasegawa
    • 1
  • M. Hattori
    • 2
  1. 1.NEC Shizuoka Ltd.Kakegawa, ShizuokaJapan
  2. 2.Yamanashi UniversityKofu, YamanashiJapan

Personalised recommendations