Skip to main content
Springer Nature Link
Log in

A Neural Associative Pattern Classifier

  • Conference paper
  • First Online:
Advances in Artificial Intelligence — IBERAMIA 2002 (IBERAMIA 2002)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 2527))

Included in the following conference series:

  • 895 Accesses

Abstract

In this work, we study the behaviour of the Bidirectional Associative Memory (BAM) in terms of the supporting neural structure, with a view to its possible improvements as a useful Pattern Classifier by means of class associations from unknown inputs, once mentioned classes have been previously defined by one or even more prototypes. The best results have been obtained by suitably choosing the training pattern pairs, the thresholds, and the activation functions of the network’s neurones, by means of certain proposed methods described in the paper. In order to put forward the advantages of these proposed methods, the classifier has been applied on an especially popular hand-written character set as the well-known NIST#19 character database, and with one of the UCI’s data bases. In all cases, the method led to a marked improvement in the performance achievable by a BAM, with a 0% error rate.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Steinbuch, K.: Die Lernmatrix. Kybernetik. 1 (1991) 36–45

    Article  Google Scholar 

  2. Anderseon, F. A.:A Simple Neural Network Generating an inter-ctive Memory. Mathematical Biosciences. 14 (1972) 197–220

    Article  Google Scholar 

  3. Kohonen, T.: Associtive Memory: A System-heoretical Approach. Springer Verlag, New York (1977)

    Google Scholar 

  4. Kosko, B.: Bidirectional Associative Memories. IEEE Trans. on Systems, Man and Cybernetics18(1) (1988) 49–60

    Article  MathSciNet  Google Scholar 

  5. Willshaw, D. J., Buneman, O. P., Longuet, H. C.: Nonholographic Associative Memory. Nature 222 (1969) 960–962. Reprinted in Anderson & Rosenfeld (eds.), Neurocomputing: Foundation of Research, MIT Press, Cam. (1998)

    Google Scholar 

  6. Sommer, F.T., Palm, G.: Improved Bidirectional Retrieval of Sparse Patterns Stored by Hebbian Learning. Neural Networks 12(2) (1999) 281–297

    Article  Google Scholar 

  7. Wang, Y. F., Cruz, J. B., Mulligan, J. H.: Two Coding Strategies for Bidirectional Associative Memory. IEEE Trans. on Neural Networks 1(1) (1991) 81–82

    Article  Google Scholar 

  8. Wang, Y. F., Cruz, J. B., Mulligan, J. H.: Guaranteed Recall of all Trainig Patterns for Bidirectional Associative Memory. IEEE Trans. on Neural Networks 2(6) (1991) 559–567

    Article  Google Scholar 

  9. Wang, Y. F., Cruz, J. B., Mulligan, J. H.: Multiple Trainig Concept for Back-Propagation Neural-Networks for use in Associative Memories. Neural Networks 6 (1993) 1169–1175

    Google Scholar 

  10. Leung, C. S., Cheung, K. F.: Householder Encoding for Discrete Bidirectional Associative Memory.Proc. of the IJCNN’91 1 (1991) 124–137

    Google Scholar 

  11. Leung. C. S.: Encoding Method for Bidirectional Associative Memory Using Projection on Convex Sets. IEEE Trans. on Neural Networks 4(5) (1993) 879–881

    Article  Google Scholar 

  12. Zhuang, X., Huang, Y., Chen, S-S.: Better Learning for Bidirectional Associative Memory. Neural networks 6 (1993) 1131–1146

    Article  Google Scholar 

  13. Arthithan, G., Dasgupta, G.: On Problem of Spurious Patterns in Neural Associtive Memory Models. IEEE Trans. on Neural Networks 8(6) (1997) 1483–1491

    Article  Google Scholar 

  14. WJeng, Y. C., Teh. C. C.: Modified Intraconnected Bidirectional Associtive Memory. IEE Electronic Letters 27(20) (1998) 1818–1819

    Article  Google Scholar 

  15. Lee, D.L.: Generalized Intraconnected Bidirectional Associtive Memories. IEE Electronic Letters 34(8) (1998) 736–738

    Article  Google Scholar 

  16. Heekuck, O. H., Kothari, S. C.: Adaptation of the Relaxation Method for Learning in Bidirectional Associative Memory. IEEE Trans. on Neural Networks 5(4) (1994) 576–583

    Article  Google Scholar 

  17. Simpson, P. K.: Higher-Ordered and Intraconnected Bidirectional Associtive Memories. IEEE Trans. on System, Man and Cybernetics 2 20(3) (1990) 637–653

    Article  Google Scholar 

  18. Park, J., Kim, H-Y, Park, Y., Lee, S-W.: A Synthesis procedure for Associtive Memories Based on Space-varying cellular Neural Networks. Neural Networks 14(1) (2001) 107–113

    Article  MathSciNet  Google Scholar 

  19. Muller, P., Rios, D.: Issues in Bayesian Analysis of Neural Network Models. Neural Computation10 (1995) 571–592

    Google Scholar 

  20. Arica, N., Yarman-Vural, T.: An Overview of Character recognition Focused on Off-line Handwriting.IEEE Trans. on Systems, MAn and Cybernetics-Part C. 31(2) (2001) 216–233

    Article  Google Scholar 

  21. Wu, Y., Pados, D. A.: A Feedforward Bidirectional Associtive Memory. IEEE Trans. on Neural Networks 11(4) (2000) 859–866

    Article  Google Scholar 

  22. Nadal, J. P., Toulouse, G.: Information Storage in Sparsely Coded Memory Nets. Network 1 (1990) 61–74

    MATH  MathSciNet  Google Scholar 

  23. Buckingham, J., Willshaw, D.: On Setting Unit Thresholds in an Incompletely Connected Associtive Net. Networks 4 (1993) 441–459

    Article  Google Scholar 

  24. Chua, L. O., Yang, L.: Cellular Neural Networks: Theory and Applications. IEEE Trans. on Circuits and Systems 35 (1988) 1257–1290

    Article  MATH  MathSciNet  Google Scholar 

  25. Kumar, S.: Memory Anhilitaion of Structured Maps in Bidirectional Associtive Memories. IEEE Trans. on Neural Networks 11(4) (2000) 1023–1038

    Article  Google Scholar 

  26. Crespi, B.: Storage Capacity of Non-monotonic Neurons. Neural Networks 12(10) (1999) 1376–1389

    Article  Google Scholar 

  27. Alippi, C., Piuri, V., Sami, M.: Sensitivity to Errors in Artificial Neural Networks:A Behavioral Approach. Proc. of the IEEE Intl. Symp. on Circuits and Systems. (1994) 1376–1389

    Google Scholar 

  28. Kretzschmar, R., Karayannis, N. B., Richner, H.: NEURO-BRA:A Bird Removal forWind Profiler Data Based on Quantum Neural Networks. Proc. of the IJCNN’2000,4 (2000) 373–378

    Google Scholar 

  29. Bollé, D., Domínguez, D. R., Amari, S. I.: Mutual Information of Sparsely CodedAssocitive Memory with Self-Control and Ternary Neurons. Neural Networks 13 (4–5) (2000) 455–462

    Article  Google Scholar 

  30. Merz, C. J., Murphy, P. M.: UCI Repository of Machine Learning Databases. (1998).Available at http://www.ics.uci.edu/~mlearn/MLRepository.html

  31. Quinlan, J. R.: Simplifying Decision Trees. International Journal of Man-Machine Studies, (1987)

    Google Scholar 

  32. Tan, M., Eshelman, L.: UsingWeighted Networks to Represent Classificatioin Knowledge in Noysi Domains. Morgan Kaufmann (eds.), Proc. of the 5th Intl. Conf. on Machine Learning (1988) 121–134

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dept. of Electronics, Faculty of Sciences, University of Extremadura, Avda. de Elvas, s/n, 06071, Badajoz, Spain

    Francisco J. López Aligué, Isabel Acevedo Sotoca, Ignacio Alvarez Troncoso, Carlos J. García Orellana & Horacio González Velasco

Authors
  1. Francisco J. López Aligué
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Isabel Acevedo Sotoca
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ignacio Alvarez Troncoso
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Carlos J. García Orellana
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Horacio González Velasco
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Telefónica Investigación y Desarrollo, Emilio Vargas 6, 28043, Madrid, Spain

    Francisco J. Garijo

  2. Dpto. Lenguajes y Sistemas Informáticos, Universidad de Sevilla, ETS Ingeniería Informática, 41012, Seville, Spain

    José C. Riquelme  & Miguel Toro  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2002 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

López Aligué, F.J., Acevedo Sotoca, I., Alvarez Troncoso, I., García Orellana, C.J., González Velasco, H. (2002). A Neural Associative Pattern Classifier. In: Garijo, F.J., Riquelme, J.C., Toro, M. (eds) Advances in Artificial Intelligence — IBERAMIA 2002. IBERAMIA 2002. Lecture Notes in Computer Science(), vol 2527. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36131-6_44

Download citation

  • DOI: https://doi.org/10.1007/3-540-36131-6_44

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-00131-7

  • Online ISBN: 978-3-540-36131-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics