Skip to main content
SpringerLink
Log in

Alpha–Beta bidirectional associative memories: theory and applications

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

In this work a new Bidirectional Associative Memory model, surpassing every other past and current model, is presented. This new model is based on Alpha–Beta associative memories, from whom it inherits its name. The main and most important characteristic of Alpha–Beta bidirectional associative memories is that they exhibit perfect recall of all patterns in the fundamental set, without requiring the fulfillment of any condition. The capacity they show is 2min(n,m), being n and m the input and output patterns dimensions, respectively. Design and functioning of this model are mathematically founded, thus demonstrating that pattern recall is always perfect, with no regard to the trained pattern characteristics, such as linear independency, orthogonality, or Hamming distance. Two applications illustrating the optimal functioning of the model are shown: a translator and a fingerprint identifier.

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

Similar content being viewed by others

References

  1. Hassoun MH (1993). Associative neural memories. Oxford University Press, New York

    MATH  Google Scholar 

  2. Kohonen T (1989). Self-organization and associative memory. Springer-Verlag, Berlin

    Google Scholar 

  3. McCulloch W and Pitts W (1943). A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5: 115–133

    Article  MATH  MathSciNet  Google Scholar 

  4. Ritter GX, Sussner P (1996) An Introduction to morphological neural networks. In Proceedings of the 13th international conference on pattern recognition, (IV) Track D pp 709–717

  5. Rosenblatt F (1958). The perceptron: a ;probabilistic model for information storage and organization in the brain. Psychol Rev 65(6): 386–408

    Article  MathSciNet  Google Scholar 

  6. Widrow B, Lehr MA (1990) 30 years of adaptive neural networks: perceptron, madaline and backpropagation. In: Proceedings of the IEEE 78(9) pp 1415–1441

  7. Werbos PJ (1990) Backpropagation through time: what it does and how to do it. In: Proceedings of the IEEE 78(10) pp 1550-1560

  8. Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. In: Proc Nat Acad Sci 79:2554–2558

  9. Minsky M and Papert S (1969). Perceptrons. MIT Press, Cambridge

    MATH  Google Scholar 

  10. Steinbuch K (1961). Die Lernmatrix. Kybernetik 1(1): 36–45

    Article  Google Scholar 

  11. Willshaw D, Buneman O and Longuet-Higgins H (1969). Non-holographic associative memory. Nature 222: 960–962

    Article  ADS  Google Scholar 

  12. Anderson JA (1972). A simple neural network generating an interactive memory. Math Biosci 14: 197–220

    Article  MATH  Google Scholar 

  13. Kohonen T (1972). Correlation matrix memories. IEEE Trans Comput C-21(4): 353–359

    Article  Google Scholar 

  14. Kosko B (1988). Bidirectional associative memories. IEEE Trans Syst Man, Cybernet 18(1): 49–60

    Article  MathSciNet  Google Scholar 

  15. Haines K and Hecht-Nielsen R (1988). A BAM with increased information storage capacity. IEEE Int Conf Neural Networks 1: 181–190

    Article  Google Scholar 

  16. Leung CS and Cheung KF (1991). Householder encoding for discrete bidirectional associative memory. IEEE Int Joint Conf Neural Networks 1: 237–241

    Article  Google Scholar 

  17. Shen D and Cruz JB (2005). Encoding strategy for maximum noise tolerance bidirectional associative memory. IEEE Trans Neural Networks 16(2): 293–300

    Article  Google Scholar 

  18. Wang Y-F, Cruz JB and Mulligan JH (1991). Guaranteed recall of all training pairs for bidirectional associative memory. IEEE Trans Neural Networks 1(6): 559–567

    Article  Google Scholar 

  19. Jiang X and Yau WY (2000). Fingerprint minutiae matching based on the local and global structures. In: Proc internat conf on pattern recognition 1038(-1041): 1038–1041

    Google Scholar 

  20. Wang Y-F, Cruz JB and Mulligan JH (1989). An enhanced bidirectional associative memory. IJCNN Int Joint Conf Neural Networks 1: 105–110

    Google Scholar 

  21. Tai H-M, Wu C-H and Jong T-L (1989). High-order bidirectional associative memory. Electron Lett 25(21): 1424–1425

    Article  Google Scholar 

  22. Jeng Y-J, Yeh C-C and Chiveh TD (1990). Exponential bidirectional associative memories. Electron Lett 26(11): 717–718

    Article  Google Scholar 

  23. Wang Y-F, Cruz JB and Mulligan JH (1990). Two coding strategies for bidirectional associative memory. IEEE Trans Neural Networks 1(1): 81–92

    Article  Google Scholar 

  24. Wang Y-F, Cruz JB and Mulligan JH (1990). On multiple training for bidirectional associative memory. IEEE Trans Neural Networks 1(3): 275–276

    Article  Google Scholar 

  25. Jeng Y-J, Yeh C-C and Chiueh T-D (1992). Generalised stable bidirectional associative memory. Electron Lett 28(15): 1396–1398

    Article  Google Scholar 

  26. Yu H, Wang Z (1992) Bidirectional associative memories on the matching criterion of weighted Hamming distance. Proceedings of the 31st IEEE conference on decision and control vol 4, pp3481–3484

  27. Lee D-L and Wang W-J (1993). Improvement of bidirectional associative memories by using correlation significance. Electron Lett 29(8): 688–690

    Article  MathSciNet  Google Scholar 

  28. Perfetti R (1993). Optimal gradient descent learning for bidirectional associative memories. Electron Lett 29(17): 1556–1557

    Article  Google Scholar 

  29. Wang W and Lee D (1993). A modified bidirectional decoding strategy based on the BAM structure. IEEE Trans Neural Network 4(4): 710–717

    Article  MathSciNet  Google Scholar 

  30. Khorasani K, Cuffaro A and Grigoriu T (1994). A new learning algorithm for bidirectional associative memory neural networks. IEEE Int Conf Neural Networks 2: 1115–1120

    Google Scholar 

  31. Xu Z-B, Leung Y and He X-W (1994). Asymmetric bidirectional associative memories. IEEE Trans Syst Man Cybernet 24(10): 1558–1564

    Article  Google Scholar 

  32. Oh H and Kothari S (1992). A Pseudo-relaxation learning algorithm for bidirectional associative memory. IJCNN 2: 208–213

    Google Scholar 

  33. Leung CS (1994). Optimum learning for bidirectional associative memory in the sense of capacity. IEEE Trans Syst, Man Cybernet 24(5): 791–796

    Article  Google Scholar 

  34. Wang Z-O (1996). A bidirectional associative memory based on optimal linear associative memory. IEEE Trans Comput 45(10): 1171–1179

    Article  MATH  Google Scholar 

  35. Sarkar D (1996). A three-stage architecture for bidirectional associative memory. IEEE Int Conf Neural Networks 1: 531/4–531/9

    Google Scholar 

  36. Haryono, Sadananda R, Phien HN (1997) Orthogonal schemes for bidirectional associative memories. IEEE Trans Syst, Man Cybernet B27(3):543-551

    Article  Google Scholar 

  37. Sadananda R, Phien HN and Haryono (1997). Orthogonal schemes for bidirectional associative memories. IEEE Trans Syst, Man Cybernet B 27(3): 543–551

    Article  Google Scholar 

  38. Ritter GX, Diazde Leon JL and Sussner P (1999). Morphological bidirectional associative memories. Neural Networks 12: 851–867

    Article  Google Scholar 

  39. Wu Y and Pados DA (2000). A feedforward bidirectional associative memory. IEEE Trans Neural Networks 11(4): 859–866

    Article  MATH  MathSciNet  Google Scholar 

  40. Liang J and Cao J (2004). Exponential stability of continuous-time and discrete time bidirectional associative memory neural networks with delays. Chaos, Solitons Fractals 22: 773–785

    Article  Google Scholar 

  41. Zheng G, Givigi SN, Zheng W (2005) A new strategy for designing bidirectional associative memories. Lecture Notes in Computer Science, vol 3496, Springer-Verlag, pp 398-403

  42. Lee D-L and Chuang TC (2004). Design of general bidirectional associative memories with improved recall capability. Int J Neural Systems 14(5): 325–328

    Article  Google Scholar 

  43. Chartier S and Boukadoum M (2006). A Bidirectional heteroassociative memory for binary and grey-level patterns. IEEE Trans Neural Networks 17(2): 385–396

    Article  Google Scholar 

  44. Arik S (2005). Global asymptotic stability analysis of bidirectional associative memory neural networks with time delays. IEEE Trans Neural Networks 16(3): 580–585

    Article  ADS  Google Scholar 

  45. Yáñez-Márquez C (2002) Associative memories based on order relations and binary operators (in Spanish) PhD Thesis. Center for Computing Research, México

  46. Acevedo ME (2006) Alpha-Beta bidirectional associative memories (in Spanish) PhD Thesis. Center for Computing Research, México

  47. http://bias.csr.unibo.it/fvc2000/download.asp

Download references

Author information

Authors and Affiliations

  1. Laboratorio de Inteligencia Artificial, Centro de Investigación en Computación, Instituto Politécnico Nacional, Av. Juan de Dios Bátiz s/n, México, DF, 07738, México

    María Elena Acevedo-Mosqueda, Cornelio Yáñez-Márquez & Itzamá López-Yáñez

Authors
  1. María Elena Acevedo-Mosqueda
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Cornelio Yáñez-Márquez
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Itzamá López-Yáñez
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to María Elena Acevedo-Mosqueda.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Acevedo-Mosqueda, M.E., Yáñez-Márquez, C. & López-Yáñez, I. Alpha–Beta bidirectional associative memories: theory and applications. Neural Process Lett 26, 1–40 (2007). https://doi.org/10.1007/s11063-007-9040-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-007-9040-2

Keywords

Search

Navigation