Skip to main content
Springer Nature Link
Log in

Evolutionary Pseudo-Relaxation Learning Algorithm for Bidirectional Associative Memory

  • Regular Paper
  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

This paper analyzes the sensitivity to noise in BAM (Bidirectional Associative Memory), and then proves the noise immunity of BAM relates not only to the minimum absolute value of net inputs (MAV) but also to the variance of weights associated with synapse connections. In fact, it is a positive monotonically increasing function of the quotient of MAV divided by the variance of weights. Besides, the performance of pseudo-relaxation method depends on learning parameters (λ and ξ), but the relation of them is not linear. So it is hard to find a best combination of λ and ξ which leads to the best BAM performance. And it is obvious that pseudo-relaxation is a kind of local optimization method, so it cannot guarantee to get the global optimal solution. In this paper, a novel learning algorithm EPRBAM (evolutionary psendo-relaxation learning algorithm for bidirectional association memory) employing genetic algorithm and pseudo-relaxation method is proposed to get feasible solution of BAM weight matrix. This algorithm uses the quotient as the fitness of each individual and employs pseudo-relaxation method to adjust individual solution when it does not satisfy constraining condition any more after genetic operation. Experimental results show this algorithm improves noise immunity of BAM greatly. At the same time, EPRBAM does not depend on learning parameters and can get global optimal solution.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Nakano K. Associatron—a model of associative memory. IEEE Trans. Syst. Man. Cybern., 1972, SMC-2: 380–388.

    Google Scholar 

  2. Hirai Y. A model of human associative processor (HASP). IEEE Trans. Syst. Man. Cybern., 1983, SMC-13: 851–857.

    Google Scholar 

  3. Hopfield J J, Neural networks and physical systems with emergent collective computational abilities. In Proc. National Academy of Science, 1982, Vol.79, pp.2554–2558.

  4. Kosko B. Bidirectional associative memories. IEEE Trans. Syst. Man. Cybern., 1988, 18: 49–60.

    Article  MathSciNet  Google Scholar 

  5. Hagiwara M. Multidirectional associative memories. International Joint Conference on Neural Networks, Washington D.C., 1990, Vol.1, pp.15–16.

  6. Hattori M, Hagiwara M. Knowledge processing system using chaos association memory. IEEE International Conference on Neural Networks, 1995, Vol.3, pp.1304–1309.

  7. Huang J, Masafumi H. A combined multi-winner multidirectional associative memory. Neural Networks, 2002, 48: 369–389.

    Google Scholar 

  8. Emilio Del-Moral-Hernandez. Neural networks with chaotic recursive nodes techniques for the design of associative memories, contrast with Hopfield architectures, and extensions for time-dependent inputs. Neural Networks, 2003, 16: 675–682.

    Article  Google Scholar 

  9. Aihara K, Takeba T, Toyoda M. Chaotic neural networks. Phisica Letters A, 1990, 144: 333–340.

    Google Scholar 

  10. Yuko O, Motonobu H, Masafumi H. Chaotic bidirectional associative memory. IEEE International Conference on Neural Networks, 1996, Vol.2, pp.816–821.

  11. Osana Y, Hattori M, Hagiwara M. Chaotic multidirectional associative memory. International Conference on Neural Networks, 1997, Vol.2, pp.1210–1215.

  12. Heekuck O, Suresh C. Adaptation of the relaxation method for learning in bidirectional associative memory. IEEE Trans. Neural Networks, 1994, 5: 576–583.

    Google Scholar 

  13. Hagiwara M. Quick learning for bidirectional associative memory. The Institute of Electronics, Information and Communication Engineers, Japan, 1994, E77-D: 385–392.

    Google Scholar 

  14. Motonobu H et al. New results of quick learning for bidirectional associative memory having high capacity. IEEE International Conference on Neural Networks, 1994, Vol.2, pp.1080–1085.

  15. Cao J D, Dong M. Exponential stability of delayed bi-directional associative memory networks. Applied Mathematics and Computation, 2003, 135: 105–112.

    Article  MathSciNet  Google Scholar 

  16. De Figueiredo R, Gerber A. Separation of superimposed pattern and many-to-many associations by chaotic neural networks. IEEE International Conference on Acoustics, Speech, and Signal Processing, 1982, Vol.7, pp.391–394.

  17. Wang Y, Cruz J B, Mulligan K H. Two coding strategies for bidirectional associative memory. Neural Networks, 1990, 1: 81–91.

    Google Scholar 

  18. Simpson P. Bidirectional associative memory systems. Tech. Rep. GDE-ISG-PKS-02, General Dynamics Electronics Div., 1988.

  19. Wang Z X, Chen Z Q, Yuan Z Z. QoS routing optimization strategy using genetic algorithm in optical fiber communication networks. J. Comput. Sci. & Technol., 2004, 19(2): 213–217.

    Google Scholar 

  20. Xu S Y, Frank T J. Forecasting the efficiency of test generation algorithms for combinational circuits. J. Comput. Sci. & Technol., 2000, 15(4): 326–337.

    Google Scholar 

  21. He J, Yao X. Time complexity analysis of an evolutionary algorithm for finding nearly maximum cardinality matching. J. Comput. Sci. & Technol., 2004, 19(4): 450–458.

    MathSciNet  Google Scholar 

  22. Li Y X, Zou X F, Kang L S et al. A new dynamical evolutionary algorithm based on statistical mechanics. J. Comput. Sci. & Technol., 2003, 18(3): 361–368.

    Google Scholar 

  23. Vassilios P, Spyros K, Anastasios B. Varying fitness functions in genetic algorithm constrained optimization: The cutting stock and unit commitment problems. IEEE Trans. Syst. Man. Cybern.—PART B: Cybernetics, 1998, 28(5): 629–640.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Automation, Nankai University, Tianjin, 300071, P.R. China

    Sheng-Zhi Du, Zeng-Qiang Chen & Zhu-Zhi Yuan

Authors
  1. Sheng-Zhi Du
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Zeng-Qiang Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Zhu-Zhi Yuan
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Sheng-Zhi Du.

Additional information

Supported by the National Natural Science Foundation of China (Grant No.60374037)

Rights and permissions

Reprints and permissions

About this article

Cite this article

Du, SZ., Chen, ZQ. & Yuan, ZZ. Evolutionary Pseudo-Relaxation Learning Algorithm for Bidirectional Associative Memory. J Comput Sci Technol 20, 559–566 (2005). https://doi.org/10.1007/s11390-005-0559-2

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11390-005-0559-2

Keywords