Skip to main content

A New Learning Strategy of General BAMs

  • Conference paper
  • 5612 Accesses

Part of the Lecture Notes in Computer Science book series (LNAI,volume 7376)

Abstract

Bi-directional Associative Memory (BAM) is an artificial neural network that consists of two Hopfield networks. The most important advantage of BAM is the ability to recall a stored pattern from a noisy input, which depends on learning process. Between two learning types of iterative learning and non-iterative learning, the former allows better noise tolerance than the latter. However, interactive learning BAMs take longer to learn. In this paper, we propose a new learning strategy that assures our BAM converges in all states, which means that our BAM recalls perfectly all learning pairs. Moreover, our BAM learns faster, more flexibility and tolerates noise better. In order to prove the effectiveness of the model, we have compared our model to existing ones by theory and by experiments.

Keywords

  • Bi-directional Associative Memory
  • Multiple Training Strategy
  • Hopfield neural network

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (Canada)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (Canada)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (Canada)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Widrow, B., Hoff, M.E.: Adaptive switching circuits. IRE WESCON Conv. Rec. 4 (1960)

    Google Scholar 

  2. Pandey, B., Ranjan, S., Shukla, A., Tiwari, R.: Sentence Recognition Using Hopfield Neural Network. IJCSNS International Journal of Computer Science Issues 7(6) (2010)

    Google Scholar 

  3. Chen, D., Li, K.: Exponential Stability of BAM Neural Networks with Delays and Impulses. IJCSNS International Journal of Computer Science and Network Security 6(10), 94–99 (2006)

    Google Scholar 

  4. Hebb, D.O.: The Organization of Behavior: A Neuropsychological Theory. Wiley, New York (1949)

    Google Scholar 

  5. Costantini, G., Casali, D., Perfetti, R.: Neural Associative Memory Storing Gray-Coded Gray-Scale Images. IEEE Transactions on Neural Networks 14(3), 703–707 (2003)

    CrossRef  Google Scholar 

  6. Shu, H.S., Lv, Z.W., Wei, G.L.: Robust stability for stochastic bidirectional associative memory neural networks with time delays. Journal of Physics, Conference Series 96 012003 (2008)

    Google Scholar 

  7. Kosko, B.: Bidirectional associative memory. IEEE Transactions on on Systems, Man, and Cybernetic 18(1) (1988)

    Google Scholar 

  8. Lenze, B.: Improving Leungs Bidirectional Learning Rule for Associative Memories. IEEE Transactions on Neural Networks 12(5), 1222–1226 (2001)

    CrossRef  Google Scholar 

  9. Leung, C.S.: Optimum Learning for Bidirectional Associative Memory in the Sense of Capacity. IEEE Transactions on Neural Networks 24(5) (1994)

    Google Scholar 

  10. Li, Z.: Dynamics in BAM Fuzzy Neural Networks with Delays and Reaction-Diffusion Terms 1(20), 979 – 1000 (2008)

    Google Scholar 

  11. Ideguchi, M., Sato, N., Osana, Y.: Hetero Chaotic Associative Memory for Successive Learning with Give Up Function. In: 2005 International Symposium on Nonlinear Theory and its Applications, pp. 42–45 (2005)

    Google Scholar 

  12. Acevedo-mosqueda, M.E., Yanez-marquez, C., Lopez-yanez, I.: Alpha-Beta Bidirectional Associative Memories Based Translator. IJCSNS International Journal of Computer Science and Network Security 6(5), 190–194 (2006)

    Google Scholar 

  13. Vazquez, R.A., Sossa, H., Garro, B.A.: A New Bi-directional Associative Memory, 367–380 (2006)

    Google Scholar 

  14. Shen, D., Cruz Jr., J.B.: Encodding strategy for maximum noise tolerance bidiretional associative memory. IEEE Transactions on Neural Networks (2003)

    Google Scholar 

  15. Singh, T.: Performance analysis of Hopfield model of neural network with evolutionary approach for pattern recalling. International Journal of Engineering Science and Technology 2(4), 504–511 (2010)

    Google Scholar 

  16. Sylvain Chartier, M.B.: A Bidirectional Heteroassociative Memory for Binary and Grey-Level Patterns. IEEE Transactions on Neural Networks 17(2), 385–396 (2006)

    CrossRef  Google Scholar 

  17. Sylvain Chartier, M.B., Amiri, M.: BAM Learning of Nonlinearly Separable Tasks by Using an Asymmetrical Output Function and Reinforcement Learning. IEEE Transactions on Neural Networks 20(8), 1281–1292 (2009)

    CrossRef  Google Scholar 

  18. Wang, T., Zhuang, X., Xing, X.: Weighted Learning of Bidirectional Associative Memories by Global Minimization. IEEE Transactions on Neural Networks 3(6) (1992)

    Google Scholar 

  19. Wang, T., Zhuang, X., Xing, X.: Memories with Optimal Stability. IEEE Transactions on Systems, Man, and Cybernetic 24(5) (1994)

    Google Scholar 

  20. Kohonen, T.: Self-organization and Associative Memory. Springer, Berlin (1988)

    MATH  Google Scholar 

  21. Wang, Y.F., Cruz Jr., J.B., Mulligan Jr., J.H.: Guaranteed recall for all training patterns of Bidirectional Associative Memory. IEEE Transactions on Neural Networks 2(6) (1991)

    Google Scholar 

  22. Chen, Y., Bi, W., Wu, Y.: Delay-Dependent Exponential Stability for Discrete-Time BAM Neural Networks with Time-Varying Delays. In: Discrete Dynamics in Nature and Society 2008, pp. 3–15 (2008)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Hoa, N.T., Duy, B.T. (2012). A New Learning Strategy of General BAMs. In: Perner, P. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2012. Lecture Notes in Computer Science(), vol 7376. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31537-4_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-31537-4_17

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-31536-7

  • Online ISBN: 978-3-642-31537-4

  • eBook Packages: Computer ScienceComputer Science (R0)