Advertisement

Analysis of Hebbian Models with Lateral Weight Connections

  • Pedro J. Zufiria
  • J. Andrés Berzal
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4507)

Abstract

In this paper, the behavior of some hebbian artificial neural networks with lateral weights is analyzed. Hebbian neural networks are employed in communications and signal processing applications for implementing on-line Principal Component Analysis (PCA). Different improvements over the original Oja model have been developed in the last two decades. Among them, models with lateral weights have been designed to directly provide the eigenvectors of the correlation matrix [1,5,6,9]. The behavior of hebbian models has been traditionally studied by resorting to an associated continuous-time formulation under some questionable assumptions which are not guaranteed in real implementations. In this paper we employ the alternative deterministic discrete-time (DDT) formulation that characterizes the average evolution of these nets and gathers the influence of the learning gains time evolution [12]. The dynamic behavior of some of these hebbian models is analytically characterized in this context and several simulations complement this comparative study.

Keywords

Lateral Weight Direct Weight Good Convergence Performance Discrete Time Stochastic System Neural Network Learn Algorithm 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Berzal, J.A., Zufiria, P.J.: Local analysis of a new Rubner-type neural network via a DDT formulation. In: Proc. of the IEEE International Symposium on Intelligent Signal Processing (WISP’2005), Faro, Portugal, p. 6 (2005)Google Scholar
  2. 2.
    Berzal, J.A., Zufiria, P.J.: Dynamic behavior of DCT and DDT formulations for the Sanger Neural Network, Neurocomputing (Accepted.)Google Scholar
  3. 3.
    Berzal, J.A., Zufiria, P.J.: Analysis of the Sanger Hebbian Neural Network. In: Cabestany, J., Prieto, A.G., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 9–16. Springer, Heidelberg (2005)Google Scholar
  4. 4.
    Berzal, A., Zufiria, P.J.: Convergence analysis of a linearized Rubner network with modified lateral weight behavior, Computational and Mathematical Methods on Science and Engineering. In: Criado, R. (ed.) 2006 Conference on Computational and Mathematical Methods on Science and Engineering, CMMSE’06, pp. 125–132 (2006)Google Scholar
  5. 5.
    Diamantaras, K.I., Kung, S.Y.: Principal Component Neural Networks: Theory and Applications. John Wiley and Sons, New York (1994)Google Scholar
  6. 6.
    Kung, S.Y., Diamantaras, K.I.: A Neural Network Learning Algorithm for Adaptive Principal Component EXtraction (APEX). In: Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, pp. 861-864 (1990)Google Scholar
  7. 7.
    Kushner, H.J., Yin, G.G.: Stochastic Approximation Algorithms and Applications. Springer, New York (1997)zbMATHGoogle Scholar
  8. 8.
    Lancaster, P., Tismenetsky, M.: The theory of matrices, 2nd edn. Academic Press, San Diego (1985)zbMATHGoogle Scholar
  9. 9.
    Rubner, J., Tavan, P.: A Selt-Organizing Network for Principal Component Analysis. Europhys. Lett. 10(7), 693–698 (1989)CrossRefGoogle Scholar
  10. 10.
    Weingessel, A., Hornik, K.: Local PCA Algorithms. IEEE Transactions on Neural Networks, 1242–1250 (November 2000)Google Scholar
  11. 11.
    Yan, W.-Y., Helmke, U., Moore, J.B.: Global Analysis of Oja’s Flow for Neural Networks. IEEE Transactions on Neural Networks, 674–683 (September 1994)Google Scholar
  12. 12.
    Zufiria, P.J.: On the Discrete-Time Dynamics of the Basic Hebbian Neural-Network Node. IEEE Transactions on Neural Networks, 1342–1352 (November 2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Pedro J. Zufiria
    • 1
  • J. Andrés Berzal
    • 1
  1. 1.Departamento de Matemática Aplicada a las Tecnologías de la Información, ETSI Telecomunicación, Univ. Politécnica de Madrid 

Personalised recommendations