A geometric newton method for oja's vector field

Neural Computation

Volumn 21, Issue 5, 2009, Pages 1415-1433

  Absil, P A ^a   Ishteva, M ^b   De Lathauwer, L ^b,c   Van Huffel, S ^b  

^a UNIVERSITÉ CATHOLIQUE DE LOUVAIN   (Belgium)

^b Katholieke Universiteit Leuven   (Belgium)

^c UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; COMPUTER SIMULATION; HUMAN; SIGNAL PROCESSING;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; COMPUTER SIMULATION; HUMANS; SIGNAL PROCESSING, COMPUTER-ASSISTED;

EID: 70349256064     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/neco.2008.04-08-749     Document Type: Letter

References (34)

1. Absil, P.-A., Edelman, A., & Koev, P. (2006). On the largest principal angle between random subspaces. Linear Algebra Appl., 414(1), 288-294.
2. Absil, P.-A., Mahony, R., & Sepulchre, R. (2004). Riemannian geometry of Grassmann manifolds with a view on algorithmic computation. Acta Appl. Math., 80(2), 199-220.
3. Absil, P.-A., Mahony, R., & Sepulchre, R. (2008). Optimization algorithms on matrix manifolds. Princeton, NJ: Princeton University Press.
4. Absil, P.-A., Sepulchre, R., & Mahony, R. (2008). Continuous-time subspace flows related to the symmetric eigenproblem. Pac. J. Optim., 4(2), 179-194.
5. Absil, P.-A., Sepulchre, R., Van Dooren, P., & Mahony, R. (2004). Cubically convergent iterations for invariant subspace computation. SIAM J. Matrix Anal. Appl., 26(1), 70-96.
6. Adler, R. L., Dedieu, J.-P., Margulies, J. Y., Martens, M., & Shub, M. (2002). Newton's method on Riemannian manifolds and a geometric model for the human spine. IMA J.Numer.Anal.,22(3), 359-390.
7. Chen, T. P., & Amari, S. (2001). Unified stabilization approach to principal and minor components extraction algorithms. Neural Networks, 14(10), 1377-1387.
8. Dehaene, J., Moonen, M., & Vandewalle, J. (1999). Analysis of a class of continuoustime algorithms for principal component analysis and subspace tracking. IEEE Trans. Circuits Systems I Fund. Theory Appl., 46(3), 364-372.
9. Dennis, J. E., Jr., & Schnabel, R. B. (1983). Numerical methods for unconstrained optimization and nonlinear equations. Englewood Cliffs, NJ: Prentice Hall.
10. Edelman, A., Arias, T. A., & Smith, S. T. (1998). The geometry of algorithms with orthogonality constraints. SIAM J. Matrix Anal. Appl., 20(2), 303-353.
11. Eisenstat, S., & Walker, H. (1996). Choosing the forcing terms in an inexact Newton method. SIAM J. Sci. Comput., 17(1), 16-32.
12. Fowler, K. R., & Kelley, C. T. (2005). Pseudo-transient continuation for nonsmooth nonlinear equations. SIAM J. Numer. Anal., 43(4), 1385-1406 (electronic).
13. Gantmacher, F. R. (1959). The theory of matrices I, II. New York: Chelsea.
14. Golub, G. H., & Van Loan, C. F. (1996). Matrix computations (3rd ed.). Baltimore, MD: Johns Hopkins University Press.
15. Higham, D. J. (1999). Trust region algorithms and timestep selection. SIAM J. Numer. Anal., 37(1), 194-210 (electronic).
16. Jankovic, M. V., & Ogawa, H. (2006). Modulated Hebb-Oja learning rule-a method for principal subspace analysis. IEEE Trans. Neural Networks, 17(2), 345-356.
17. Kelley, C. T., Qi, L., Liao, L.-Z., Reese, J. P., & Winton, C. (2006). Pseudo-transient continuation and optimization. Available online at http://www4.ncsu.edu/~ctk/pubs.html.
18. Kobayashi, S., & Nomizu, K. (1963). Foundations of differential geometry. New York: Wiley.
19. Lee, J. M. (2003). Introduction to smooth manifolds.NewYork:Springer-Verlag.
20. Lundström, E., & Eldén, L. (2001-2002). Adaptive eigenvalue computations using Newton's method on the Grassmann manifold. SIAM J. Matrix Anal. Appl., 23(3) 819-839.
21. Luo, X.-L., Kelley, C. T., Liao, L.-Z., & Tam, H.-W. (2006). Combining trust region techniques and Rosenbrock methods for gradient systems. Available online at http://www4.ncsu.edu/~ctk/pubs.html.
22. Manton, J. H., Helmke, U., & Mareels, I. M. Y. (2005). A dual purpose principal and minor component flow. Systems Control Lett., 54(8), 759-769.
23. Oja, E. (1982). A simplified neuron model as a principal component analyzer. J. Math. Biol., 15, 267-273.
24. Oja, E. (1989). Neural networks, principal components, and subspaces. Int. J. Neural Syst., 1, 61-68.
25. Oja, E., Ogawa, H., & Wangviwattana, J. (1992a). Principal component analysis by homogeneous neural networks, Part II: Analysis and extensions of the learning algorithms. IEICE Trans. Inf. Syst., 3, 376-382.
26. Oja, E., Ogawa, H., & Wangviwattana, J. (1992b). Principal component analysis by homogeneous neural networks, part I: The weighted subspace criterion. IEICE Trans. Inf. Syst., 3, 366-375.
27. O'Neill, B. (1983). Semi-Riemannian geometry. New York: Academic Press.
28. Ortega, J. M., & Rheinboldt, W. C. (1970). Iterative solution of nonlinear equations in several variables. New York: Academic Press.
29. Smith, S. T. (1994). Optimization techniques on Riemannian manifolds. In A. Bloch (Ed.), Hamiltonian and gradient flows, algorithms and control (Vol. 3, pp. 113-136). Providence, RI: American Mathematical Society.
30. Xu, L. (1993). Least mean square error reconstruction principle for self-organizing neural-nets. Neural Networks, 6(5), 627-648.
31. Yan, W.-Y. (1998). Stability and convergence of principal component learning algorithms. SIAM J. Matrix Anal. Appl., 19(4), 933-955 (electronic).
32. Yan, W.-Y., Helmke, U., & Moore, J. B. (1994). Global analysis of Oja's flow for neural networks. IEEE Trans. on Neural Networks, 5(5), 674-683.
33. Yoshizawa, S., Helmke, U., & Starkov, K. (2001). Convergence analysis for principal component flows. Int. J. Appl. Math. Comput. Sci., 11(1), 223-236.
34. Yoshizawa, S., Helmke, U., & Starkov, K. (2002). Corrections to "Convergence analysis for principal component flows." Int. J. Appl. Math. Comput. Sci., 12(2), 299.