On the discrete-time dynamics of the basic Hebbian neural-network node

IEEE Transactions on Neural Networks

Volumn 13, Issue 6, 2002, Pages 1342-1352

  Zufiria, Pedro J ^a  

^a UNIVERSIDAD POLITÉCNICA DE MADRID   (Spain)

Author keywords

Chaos; Dynamical behavior; Hebbian neural networks (NNs); Stochastic approximation

Indexed keywords

APPROXIMATION THEORY; COMPUTATIONAL METHODS; COMPUTER SIMULATION; LEARNING SYSTEMS;

DISCRETE-TIME DYNAMICS;

NEURAL NETWORKS;

EID: 0036858172     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2002.805752     Document Type: Article

References (20)

1. F.T. Arecchi, R. Badii, and A. Politi, "Low-frequency phenomena in dynamical systems with many attractors," Phys. Rev. A, vol. 29, no. 2, pp. 1006-1009, 1984.
2. J.A. Berzal, P.J. Zufiria, and L. Rodríguez, "Implementing the Karhunen-Loeve transform via improved neural networks," in Proc. Int. Conf. Eng. Applicat. Neural Networks: Solving Eng. Problems Neural Networks, London, U.K., 1996, pp. 375-378.
3. K.I. Diamantaras and S.Y. Kung, Principal Component Neural Networks. Theory and Applications. New York: Wiley, 1996.
4. H.J. Kushner and H. Huang, "Asymptotic properties of stochastic approximations with constant coefficients," SIAM J. Contr. Optimization, vol. 19, no. 1, pp. 87-105, 1981.
5. H.J. Kushner and G.G. Yin, Stochastic Approximation Algorithms and Applications. New York: Springer-Verlag, 1997.
6. S. Haykin, Neural Networks. A Comprehensive Foundation. New York: Macmillan, 1994.
7. C.S. Hsu, Cell-to-Cell Mapping: A Method of Global Analysis for Nonlinear Systems. New York: Springer-Verlag, 1987.
8. R.-W. Liu, Y.-F. Huang, and X.-T. Ling, "A novel approach to the convergence of neural networks for signal processing," IEEE Trans. Circuits Syst., vol. 42, pp. 187-188, Mar. 1995.
9. L. Ljung, "Analysis of recursive stochastic algorithms," IEEE Trans. Automat. Contr., vol. AC-22, pp. 551-575, Mar. 1977.
10. E. Oja, "A simplified neuron model as a principal component analyzer," J. Math. Biol., vol. 15, pp. 267-273, 1982.
11. F. Peper and H. Noda, "A symmetric linear neural network that learns principal components and their variances," IEEE Trans. Neural Networks, vol. 7, pp. 1042-1047, July 1996.
12. M.D. Plumbley, "Lyapunov functions for convergence of principal component algorithms," Neural Networks, vol. 8, no. 1, pp. 11-23, 1995.
13. H. Robbins and S. Monro, "A stochastic approximation method," Ann. Math. Statist., vol. 22, pp. 400-407, 1951.
14. T.D. Sanger, "Optimal unsupervised learning in a single-layer linear feedforward neural network," Neural Networks, vol. 2, pp. 459-473, 1989.
15. A.M. Stuart and A.R. Humphries, Dynamical Systems and Numerical Analysis. Cambridge, U.K.: Cambridge Univ. Press, 1996.
16. J. Testa and G.A. Help, "Study of a one-dimensional map with multiple basins," Phys. Rev. A, vol. 28, no. 3, pp. 3085-3089, 1983.
17. W.-Y. Yan, U. Helmke, and J.B. Moore, "Global analysis of Oja's flow for neural networks," IEEE Trans. Neural Networks, vol. 5, pp. 674-683, Sept. 1994.
18. Q. Zhang and Z. Bao, "Dynamical system for computing the eigenvectors associated with the largest eigenvalue of a positive definite matrix," IEEE Trans. Neural Networks, vol. 6, pp. 790-791, May 1995.
19. Q. Zhang and Y.W. Leung, "Energy function for one-unit oja algorithm," IEEE Trans. Neural Networks, vol. 6, pp. 1291-1293, Sept. 1995.
20. P.J. Zufiria, "Global behavior of a class of nonlinear dynamical systems: Analytical computational and control aspects," Ph.D. dissertation, Univ. Southern California, Los Angeles, 1989.