Global Analysis of Oja’s Flow for Neural Networks

IEEE Transactions on Neural Networks

Volumn 5, Issue 5, 1994, Pages 674-683

  Yan, Wei Yong ^a   Helmke, Uwe ^b   Moore, John B ^a  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

^b UNIVERSITY OF REGENSBURG   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; CONVERGENCE OF NUMERICAL METHODS; CORRELATION METHODS; EIGENVALUES AND EIGENFUNCTIONS; LEARNING SYSTEMS; MATRIX ALGEBRA; NUMERICAL ANALYSIS; NUMERICAL METHODS; VECTORS;

AUTOCORRELATION MATRIX; EIGENSPACE; EXISTENCE; MONOTONICITY; OJAS LEARNING EQUATION; RAYLEIGH QUOTIENTS; UNIQUENESS;

NEURAL NETWORKS;

EID: 0028496455     PISSN: 10459227     EISSN: 19410093     Source Type: Journal    
DOI: 10.1109/72.317720     Document Type: Article

References (14)

1. P. Baldi and K. Hornik, “Back propagation and unsupervised learning in linear networks,” in Back Propagation: Theory, Architectures and Applications, Y. Chauvin and D. E. Rummelhart, Eds. Earlbaum Associates, 1991.
2. R. W. Brockett, “Dynamical systems that sort lists, diagonalize matrices and solve linear programming problems,” Proc. 27th Conf. Decision and Contr., pp. 799–803, 1988.
3. U. Helmke and J. B. Moore, Optimization and Dynamical Systems. New York: Springer-Verlag 1993.
4. M. W. Hirsch and S. Smale, Differential Equations, Dynamical Systems, and Linear Algebra. New York: Academic Press, 1974.
5. K. Hornik and C. M. Kuan, “Convergence analysis of local feature extraction algorithms,” Neural Networks, vol 5, pp. 229–240, 1992.
6. A. Krogh and J. Hertz, “Hebbian learning of principal components,” in Parallel Processing in Neural Systems and Computers, R. Eckmiller, G. Hartmann, and G. Hauske, Eds. Amsterdam: Elsevier Science Publishers B. V., North-Holland, 1990, 183–186.
7. C. M. Kuan and K. Hornik, “Convergence of learning algorithms with constant rates,” IEEE Trans. Neural Networks, vol. 2, pp. 484-489,1991.
8. E. Oja, “A simplified neuron model as a principal component analyzer,” J. Math. Biol., vol 15, pp. 267–273, 1982.
9. E. Oja, Subspace methods of pattern recognition. Letchworth, England: Research Studies Press, 1983.
10. E. Oja, “Neural networks, principal components, and subspaces,” Int. J. Neural Syst., vol 1, pp. 61–68, 1989.
11. E. Oja and J. Karhunen, “On stochastic approximation of eigenvectors and eigenvalues of the expectation of a random matrix,” J. M. A. A., vol 106, pp. 69–84, 1985.
12. T. Sasagawa, “On the finite escape phenomena for matrix Riccati equations,” IEEE Trans. Automat. Contr., vol. 27, pp. 977–978, 1982.
13. D. W. Tank and J. J. Hopfield, “Simple 'neural’ optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit,” IEEE Trans. Circuits Syst., vol. 33, pp. 533–541, 1985.
14. R. Williams, “Feature discovery through error-correcting learning,” Technical Report 8501, UCSD, Institute of Cognitive Science, 1985.