Improving VG-RAM Neural Networks Performance Using Knowledge Correlation

  • Raphael V. Carneiro
  • Stiven S. Dias
  • Dijalma FardinJr.
  • Hallysson Oliveira
  • Artur S. d’Avila Garcez
  • Alberto F. De Souza
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4232)


In this work, the correlation between input-output patterns stored in the memory of the neurons of Virtual Generalizing RAM (VG-RAM) weightless neural networks, or knowledge correlation, is used to improve the performance of these neural networks. The knowledge correlation, detected using genetic algorithms, is used for changing the distance function employed by VG-RAM neurons in their recall mechanism. In order to evaluate the performance of the method, experiments with several well-known datasets were made. The results showed that VG-RAM networks employing knowledge correlation perform significantly better than standard VG-RAM networks.


Genetic Algorithm Lookup Table Wisconsin Breast Cancer Cascade Correlation Wisconsin Breast Cancer Dataset 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aleksander, I.: Self-adaptive Universal Logic Circuits (Design Principles and Block Diagrams of Self-adaptive Universal Logic Circuit with Trainable Elements). IEE Electronic Letters 2, 231–232 (1966)Google Scholar
  2. 2.
    Ludermir, T.B., Carvalho, A., Braga, A.P., Souto, M.C.P.: Weightless Neural Models: A Review of Current and Past Works. Neural Computing Surveys 2, 41–61 (1999)Google Scholar
  3. 3.
    Aleksander, I.: From WISARD to MAGNUS: a family of weightless virtual neural machines. In: Austin, J. (ed.) RAM-Based Neural Networks, pp. 18–30. World Scientific, Singapore (1998)Google Scholar
  4. 4.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley, Reading (1989)MATHGoogle Scholar
  5. 5.
    Komati, K.S., De Souza, A.F.: Using Weightless Neural Networks for Vergence Control in an Artificial Vision System. Applied Bionics and Biomechanics 1, 21–32 (2003)CrossRefGoogle Scholar
  6. 6.
    Aleksander, I., Browne, C., Dunmall, B., Wright, T.: Towards Visual Awareness in a Neural System. In: Amari, S., Kasabov, N. (eds.) Brain-Like Computing and Intelligent Information Systems, pp. 513–533. Springer, Heidelberg (1997)Google Scholar
  7. 7.
    Corcoran, A.L., Wainwright, R.L.: LibGA: A User-friendly Workbench for Order-based Genetic Algorithm Research. In: Proceedings of the ACM/SIGAPP Symposium on Applied Computing: States of the Art and Practice, pp. 111–117 (1993)Google Scholar
  8. 8.
    Newman, D.J., Hettich, S., Blake, C.L., Merz, C.J.: UCI Repository of Machine Learning Databases. University of California, Department of Information and Computer Science, Irvine, CA (1998),
  9. 9.
    Thrun, S.B., et al.: The MONK’s Problems: A Performance Comparison of Different Learning Algorithms. Technical Report CS-CMU-91-197, Carnegie Mellon University (1991)Google Scholar
  10. 10.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice-Hall, Englewood Cliffs (1998)Google Scholar
  11. 11.
    Fahlman, S.E., Lebiere, C.: The Cascade-correlation Learning Architecture. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 2, pp. 524–532. Morgan Kaufmann, San Francisco (1990)Google Scholar
  12. 12.
    Vafaie, H., De Jong, K.A.: Improving the Performance of a Rule Induction System Using Genetic Algorithms. In: Proceedings of the First International Workshop on Multistrategy Learning, pp. 305–315. Harpers Ferry, W. Virginia (1991)Google Scholar
  13. 13.
    Wnek, J., Michalski, R.S.: Hypothesis-driven Constructive Induction in AQ17: A Method and Experiments. Machine Learning 14(2), 139–168 (1994)MATHCrossRefGoogle Scholar
  14. 14.
    Wolberg, W.H., Mangasarian, O.L.: Multisurface Method of Pattern Separation for Medical Diagnosis Applied to Breast Cytology. Proceedings of the National Academy of Sciences, U.S.A. 87, 9193–9196 (1990)MATHCrossRefGoogle Scholar
  15. 15.
    Rohwer, R., Morciniec, M.: A Theoretical and Experimental Account of N-tuple Classifier Performance. Neural Computing 8, 629–642 (1995)CrossRefGoogle Scholar
  16. 16.
    Salamó, M., Golobardes, E., Vernet, D., Nieto, M.: Weighting Methods for a Case-based Classifier System. In: Proceedings of Learning 2000, Madrid, Spain (2000)Google Scholar
  17. 17.
    Webb, G.I.: Further Experimental Evidence Against the Utility of Occam’s Razor. Journal of Artificial Intelligence Research 4, 397–417 (1996)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Raphael V. Carneiro
    • 1
  • Stiven S. Dias
    • 1
  • Dijalma FardinJr.
    • 1
  • Hallysson Oliveira
    • 1
  • Artur S. d’Avila Garcez
    • 2
  • Alberto F. De Souza
    • 1
  1. 1.Programa de Pós-Graduação em InformáticaUniversidade Federal do Espírito SantoVitóriaBrazil
  2. 2.Department of ComputingCity UniversityLondonUK

Personalised recommendations