User menu

A Geometric Newton Method for Oja's Vector Field.

Bibliographic reference Absil, Pierre-Antoine ; Ishteva, Mariya ; De Lathauwer, Lieven ; Van Huffel, Sabine. A Geometric Newton Method for Oja's Vector Field.. In: Neural computation, Vol. 21, no. 5, p. 1415-33 (2009)
Permanent URL http://hdl.handle.net/2078.1/19703
  1. Absil P.-A., Edelman A., Koev P., On the largest principal angle between random subspaces, 10.1016/j.laa.2005.10.004
  2. Absil P.-A., Mahony R., Sepulchre R., Riemannian Geometry of Grassmann Manifolds with a View on Algorithmic Computation, 10.1023/b:acap.0000013855.14971.91
  3. Absil P.-A., Mahony R., Sepulchre R., Optimization Algorithms on Matrix Manifolds : , ISBN:9781400830244, 10.1515/9781400830244
  4. Absil P.-A., Pac. J. Optim., 4, 179 (2008)
  5. Absil P. A., Sepulchre R., Van Dooren P., Mahony R., Cubically Convergent Iterations for Invariant Subspace Computation, 10.1137/s0895479803422002
  6. Adler R. L., Newton's method on Riemannian manifolds and a geometric model for the human spine, 10.1093/imanum/22.3.359
  7. Chen Tianping, Amari Shun-ichi, Unified stabilization approach to principal and minor components extraction algorithms, 10.1016/s0893-6080(01)00116-2
  8. Dehaene J., Moonen M., Vandewalle J., Analysis of a class of continuous-time algorithms for principal component analysis and subspace tracking, 10.1109/81.751309
  9. Dennis J. E., Numerical methods for unconstrained optimization and nonlinear equations (1983)
  10. Edelman Alan, Arias Tomás A., Smith Steven T., The Geometry of Algorithms with Orthogonality Constraints, 10.1137/s0895479895290954
  11. Eisenstat Stanley C., Walker Homer F., Choosing the Forcing Terms in an Inexact Newton Method, 10.1137/0917003
  12. Fowler K. R., Kelley C. T., Pseudo-Transient Continuation for Nonsmooth Nonlinear Equations, 10.1137/s0036142903431298
  13. Gantmacher F. R., The theory of matrices I, II (1959)
  14. Golub G. H., Matrix computations (1996)
  15. Higham Desmond J., Trust Region Algorithms and Timestep Selection, 10.1137/s0036142998335972
  16. Jankovic M.V., Ogawa H., Modulated Hebb–Oja Learning Rule—A Method for Principal Subspace Analysis, 10.1109/tnn.2005.863455
  17. Kobayashi S., Foundations of differential geometry (1963)
  18. Lee John M., Introduction to Smooth Manifolds, ISBN:9780387954486, 10.1007/978-0-387-21752-9
  19. Lundström Eva, Eldén Lars, Adaptive Eigenvalue Computations Using Newton's Method on the Grassmann Manifold, 10.1137/s0895479899354688
  20. Manton Jonathan H., Helmke Uwe, Mareels Iven M.Y., A dual purpose principal and minor component flow, 10.1016/j.sysconle.2004.11.015
  21. Oja Erkki, Simplified neuron model as a principal component analyzer, 10.1007/bf00275687
  22. Oja Erkki, NEURAL NETWORKS, PRINCIPAL COMPONENTS, AND SUBSPACES, 10.1142/s0129065789000475
  23. Oja E., IEICE Trans. Inf. Syst., 3, 376 (1992)
  24. Oja E., IEICE Trans. Inf. Syst., 3, 366 (1992)
  25. O'Neill B., Semi-Riemannian geometry (1983)
  26. Ortega J. M., Iterative solution of nonlinear equations in several variables (1970)
  27. Smith S. T., Hamiltonian and gradient flows, algorithms and control, 3, 113 (1994)
  28. Xu Lei, Least mean square error reconstruction principle for self-organizing neural-nets, 10.1016/s0893-6080(05)80107-8
  29. Yan Wei-Yong, Stability and Convergence of Principal Component Learning Algorithms, 10.1137/s0895479896310329
  30. Wei-Yong Yan, Helmke U., Moore J.B., Global analysis of Oja's flow for neural networks, 10.1109/72.317720
  31. Yoshizawa S., Int. J. Appl. Math. Comput. Sci., 11, 223 (2001)
  32. Yoshizawa S., Int. J. Appl. Math. Comput. Sci., 12, 299 (2002)