Advertisement

Alpha-Beta Weightless Neural Networks

  • Amadeo José Arguelles-Cruz
  • Itzamá López-Yáñez
  • Mario Aldape-Pérez
  • Napoleón Conde-Gaxiola
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5197)

Abstract

A novel weightless neural network model is presented, based on the known operations Alpha and Beta, and three original operations proposed. The new model of weightless neural network has been called CAINN – Computing Artificial Intelligent Neural Network. The experimental aspect is presented by applying the CAINN model to several known databases. Also, comparative studies about the performance of the CAINN model concerning ADAM weightless neural network and other models are reported. Results exhibit the superiority of the CAINN model over the ADAM model, its counterpart as a weightless neural network; and over other models immersed in the state of the art of neural networks; taking into account the No Free Lunch theorem.

Keywords

Weightless Neural Networks ADAM CAINN Classifier No Free Lunch 

References

  1. 1.
    Bledsoe, W.W., Browning, I.: Pattern Recognition and Reading by machine. In: Proc. Eastern Joint Computer Conference, pp. 225–232 (1959)Google Scholar
  2. 2.
    Aleksander, I.: Canonical neural nets based on logic nodes. In: First IEE International Conference on Artificial Neural Networks, pp. 110–114. IEEE, London (1989)Google Scholar
  3. 3.
    Kan, W.K., Aleksander, I.: A probabilistic logic neuron network for associative learning. In: Proceedings of the IEEE First International Conference on Neural Networks, ICNN 1987, pp. 541–548 (1987)Google Scholar
  4. 4.
    Myers, C.E., Aleksander, I.: Output functions for probabilistic logic nodes. In: First IEE International Conference on Artificial Neural Networks, pp. 310–314 (1989)Google Scholar
  5. 5.
    Aleksander, I., Thomas, W.V., Bowden, P.A.: WISARD, a Radical Step Forward in Image Recognition. Sensor Review 4(3), 120–124 (1984)CrossRefGoogle Scholar
  6. 6.
    Ludermir, T.B., et al.: Weightless Neural Models: A Review of Current and Past Works. Neural Computing Surveys 2, 41–61 (1999)Google Scholar
  7. 7.
    Austin, J.: RAM based neural networks, a short history. In: RAM-Based Neural Networks. World Scientific Publishing Co. Pte. Ltd, Singapore (1998)CrossRefGoogle Scholar
  8. 8.
    Austin, J.: Grey scale n-tuple processing. Springer, Berlin (1988)CrossRefGoogle Scholar
  9. 9.
    Austin, J.: ADAM: A Distributed Associative Memory for Scene Analysis. In: Caudhill, M., Butler, C. (eds.) Proceedings of First International Conference on Neural Networks, San Diego, CA, pp. 285–295 (1987)Google Scholar
  10. 10.
    Al-Alawi, R.: FPGA Implementation of a Pyramidal Weightless Neural Networks Learning System. International Journal of Neural Systems 13(4), 225–237 (2003)CrossRefGoogle Scholar
  11. 11.
    Argüelles, A.J., Díaz De Leon, J.L., Yañez, C., Camacho, C.: Pattern recognition and classification using weightless neural networks and Steinbuch Lernmatrix. In: SPIE Optics and Photonics 2005. SPIE, pp. (59160)P1-P8 (2005)Google Scholar
  12. 12.
    Howells, G., Fairhurst, M.C., Rahman, F.: An exploration of a new paradigm for weightless RAM-based neural networks. Connection Science 12(1), 65–90 (2000)CrossRefGoogle Scholar
  13. 13.
    Yáñez-Márquez, C.: Memorias Asociativas basadas en Relaciones de Orden y Operadores Binarios (in Spanish). Ph.D. Thesis. National Polytechnics Institute, Computers Research Center, Mexico (2002)Google Scholar
  14. 14.
    Tran, Q., Toh, K., Srinivasan, D., Wong, K., Low, S.Q.: An empirical comparison of nine pattern classifiers. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 35(5), 1079–1091 (2005)CrossRefGoogle Scholar
  15. 15.
    Abdullah, M.R.B., Toh, K., Srinivasan, D.: A framework for empirical classifiers comparison. In: 1st IEEE Conference on Industrial Electronics and Applications, art. no. 4026002 (2006)Google Scholar
  16. 16.
    Asuncion, A., Newman, D.J.: UCI Machine Learning Repository. University of California, School of Information and Computer Science. Irvine, CA, U. S. A (2007), http://www.ics.uci.edu/~mlearn/MLRepository.html
  17. 17.
    Demsar, J.: Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research 7, 1–30 (2006)MathSciNetzbMATHGoogle Scholar
  18. 18.
    Wolpert, D.H., Macready, W.G.: No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation 1(1), 67–82 (1997)CrossRefGoogle Scholar
  19. 19.
    Wolpert, D.H.: The supervised learning no-free-lunch theorems. In: Proceedings of the 6th Online World Conference on Soft Computing in Industrial Applications (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Amadeo José Arguelles-Cruz
    • 1
  • Itzamá López-Yáñez
    • 1
  • Mario Aldape-Pérez
    • 1
  • Napoleón Conde-Gaxiola
    • 1
  1. 1.IPN Centro de Investigación en Computación, Juan de Dios Bátiz s/n esq. Miguel Othón de Mendizábal, Unidad Profesional Adolfo López Mateos, Del. Gustavo A. MaderoD.F. MéxicoMéxico

Personalised recommendations