Global convergence of Oja's subspace algorithm for principal component extraction

IEEE Transactions on Neural Networks

Volumn 9, Issue 1, 1998, Pages 58-67

  Chen, Tianping ^a,b   Hua, Yingbo ^a,c   Yan, Wei Yong ^d  

^a IEEE   (China)

^b FUDAN UNIVERSITY   (China)

^c UNIVERSITY OF MELBOURNE   (Australia)

^d NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

Author keywords

Convergence rate; Global convergence; Principal components extraction

Indexed keywords

ASYMPTOTIC STABILITY; CONVERGENCE OF NUMERICAL METHODS; DIFFERENTIAL EQUATIONS; EIGENVALUES AND EIGENFUNCTIONS; FEATURE EXTRACTION; MATRIX ALGEBRA; TIME SERIES ANALYSIS;

DATA COVARIANCE MATRIX; INITIAL WEIGHT MATRIX; OJA'S SUBSPACE ALGORITHMS; PRINCIPAL COMPONENT EXTRACTION;

PARALLEL ALGORITHMS;

EID: 0031672308     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.655030     Document Type: Article

References (11)

1. S. I. Amari, "Neural theory of association and concept-formation," Biol. Cybern., vol. 26, pp. 175-185, 1977
2. E. Oja, "A simplified neuron model as a principal component analyzer," J. Math. Biol., vol. 15, pp. 267-273, 1982.
3. E. Oja and J. Karhunen, "On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix," J. Math. Anal. Applicat., vol. 106, pp. 69-84, 1985.
4. E. Oja, "Neural networks, principal components, and subspaces," Int. J. Neural Syst., vol. 1, pp. 61-68, 1989.
5. _, "Principal components, minor components, and linear neural networks," Neural Networks, vol. 5, pp. 927-935, 1992.
6. K. Hornik and C. M. Kuan, "Convergence analysis of local feature extraction algorithms," Neural Networks, vol. 5, pp. 229-240, 1992.
7. P. Baldi and K. Hornik, "Learning in linear neural networks: A survey," IEEE Trans. Neural Networks, vol. 6, pp. 837-858, 1995.
8. L. Xu, L. Krzyzak, and E. Oja, "Neural nets for dual subspace pattern recognition method," Int. J. Neural Syst., vol. 2, pp. 169-184, 1991.
9. L. Xu, "Least mean square error recognition principle for self-organizing neural nets," Neural Networks, vol. 6, pp. 627-648, 1993.
10. 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, 1994.
11. G. H. Golub and Van Loan, Matrix Computation. Baltimore, MD: John Hopkins Univ. Press, 1985, p. 271.