Skip to main content
SpringerLink
Log in

The effect of weight fault on associative networks

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In the past three decades, the properties of associative networks has been extensively investigated. However, most existing results focus on the fault-free networks only. In implementation, network faults can be exhibited in different forms, such as open weight fault and multiplicative weight noise. This paper studies the effect of weight fault on the performance of the bidirectional associative memory (BAM) model when multiplicative weight noise and open weight fault present. Assuming that connection weights are corrupted by these two common fault models, we study how many number of pattern pairs can be stored in a faulty BAM. Since one of important feature of associative network is error correction, we also study the number of pattern pairs can be stored in a faulty BAM when there are some errors in the initial stimulus pattern.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Kohonen T (1972) Correlation matrix memories. IEEE Trans Comput 21:353–359

    Article  MATH  Google Scholar 

  2. Palm G (1980) On associative memory. Biolog Cybern 36:19–31

    Article  MATH  Google Scholar 

  3. Kosko B (1988) Bidirectional associative memories. IEEE Trans Syst Man Cybern 18:49–60

    Article  MathSciNet  Google Scholar 

  4. Haines K, Hecht-Nielsen R (1988) A bam with increased information storage capacity. In: Proceedings of the 1988 IEEE international conference on neural networks, pp 181–190

  5. Amari S (1988) Statistical neurodynamics of various versions of correlation associative memory. In: Proceedings of the 1988 IEEE international conference on neural networks, pp 181–190

  6. Oapos SEM, Austin J (1994) An application of an associative memory to the analysis of document images. In: Proceedings of the British machine vision conference

  7. Chau FT, Cheung B, Tam KY, Li LK (1995) Application of a bi-directional associative memory (bam) network in computer assisted learning in chemistry. Comput chem 18(4):359–362

    Article  Google Scholar 

  8. Ruz-Hernandez JA, Sanchez EN, Suarez DA (2006) Designing an associative memory via optimal training for fault diagnosis. In: Proceedings of IJCNN’06, pp 4338–4345

  9. Wang YF, Cruz JB, Mulligan JH (1990) Two coding strategies for bidirectional associative memory. IEEE Trans Neural Netw 1:81–92

    Article  Google Scholar 

  10. Leung CS (1993) Encoding method for bidirectional associative memory using projection on convex sets. IEEE Trans Neural Netw 4:879–991

    Article  Google Scholar 

  11. Leung CS (1994) Optimum learning for bidirectional associative memory in the sense of capacity. IEEE Trans Syst Man Cybern 24:791–796

    Article  Google Scholar 

  12. Lenze B (2001) Improving Leung’s bidirectional learning rule for associative memories. IEEE Trans Neural Netw 12:1222–1226

    Article  Google Scholar 

  13. Shen D, Cruz JB (2005) Encoding strategy for maximum noise tolerance bidirectional associative memory. IEEE Trans Neural Netw 16:293–300

    Article  Google Scholar 

  14. Simpson PK (1990) Higher-ordered and intraconnected bidirectional associative memories. IEEE Trans Syst Man Cybern 20:637–653

    Article  Google Scholar 

  15. Leung CS, Chan LW (1997) The behavior of forgetting learning in bidirectional associative memory. Neural Comput 9:385–401

    Article  MATH  Google Scholar 

  16. Leung CS, Chan LW, Lai E (1997) Stability and statistical properties of second-order bidirectional associative memory. IEEE Trans Neural Netw 8:267–277

    Article  Google Scholar 

  17. Burr JB (1991) Digital neural network implementations. Neural Netw Concepts Appl Implement III:237–285

    Google Scholar 

  18. Himavathi S, Anitha D, Muthuramalingam A (2007) Feedforward neural network implementation in fpga using layer multiplexing for effective resource utilization. IEEE Trans Neural Netw 18:880–888

    Article  Google Scholar 

  19. Antony MM, Savich W, Areibi S (2007) The impact of arithmetic representation on implementing mlp-bp on fpgas: a study. IEEE Trans Neural Netw 18:240–252

    Article  Google Scholar 

  20. Kaneko T, Liu B (1970) Effect of coefficient rounding in floating-point digital filters. IEEE Trans Aerosp Electron Syst AE-7:995–1003

    Google Scholar 

  21. Liu B, Kaneko T (1969) Error angalysis of digital filter realized with floating-point arithemetic. Proc IEEE 57:1735–1747

    Article  Google Scholar 

  22. Phatak DS, Koren I (1995) Complete and partial fault tolerance of feedforward neural nets. IEEE Trans Neural Netw 6:446–456

    Article  Google Scholar 

  23. Emmerson MD, Damper RI (1993) Determining and improving the fault tolerance of multilayer perceptrons in a pattern-recognition application. IEEE Trans Neural Netw 4:788–793

    Article  Google Scholar 

  24. Zhou ZH, Chen SF (2003) Evolving fault-tolerant neural networks. Neural Comput Appl 11:156–160

    Article  MATH  Google Scholar 

  25. Sing LC, John S (2008) A fault-tolerant regularizer for rbf networks. IEEE Trans Neural Netw 19:493–507

    Article  Google Scholar 

  26. Bolt G (1991) Fault models for artificial neural networks. In: 1991 IEEE international joint conference on neural networks, vol 2, pp 1373–1378

  27. Sossa H, Barron R, Vazquez RA (2007) Study of the influence of noise in the values of a median associative memory. In: ICANNGA 2007 (2), NCS 4432

Download references

Acknowledgements

The work presented in this paper is supported by a research grant from the City University of Hong Kong (Project No. 7002480).

Author information

Authors and Affiliations

  1. Department of Electronic Engineering, The City University of Hong Kong, Kowloon Tong, Hong Kong

    Andrew Chi-Sing Leung

  2. Institute of Electronic Commerce, National Chung Hsing University, Taichung, Taiwan

    Pui Fai Sum

  3. Department of Computer Science and Communication Engineering, Providence University, Shalu, Taiwan

    Kevin Ho

Authors
  1. Andrew Chi-Sing Leung
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pui Fai Sum
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kevin Ho
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrew Chi-Sing Leung.

Additional information

The work presented in this paper is supported by a research grant from the City University of Hong Kong (Project No. 7002480).

Rights and permissions

Reprints and permissions

About this article

Cite this article

Leung, A.CS., Sum, P.F. & Ho, K. The effect of weight fault on associative networks. Neural Comput & Applic 20, 113–121 (2011). https://doi.org/10.1007/s00521-010-0351-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-010-0351-2

Keywords

Search

Navigation