Learning by natural gradient on noncompact matrix-type pseudo-riemannian manifolds

IEEE Transactions on Neural Networks

Volumn 21, Issue 5, 2010, Pages 841-852

  Fiori, Simone ^a  

^a UNIVERSITÀ POLITECNICA DELLE MARCHE   (Italy)

Author keywords

Geodesic stepping; Learning by optimization; Learning on noncompact manifolds; Natural gradient

Indexed keywords

CLOSED FORM; GENERAL THEORY; GEODESIC CURVES; GRADIENT OPTIMIZATION; GRADIENT-BASED LEARNING; LEARNING BY OPTIMIZATION; MATRIX; NATURAL GRADIENT; RIEMANNIAN MANIFOLD; RIEMANNIAN METRICS;

GEODESY;

OPTIMIZATION;

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; ARTIFICIAL NEURAL NETWORK; HUMAN; LEARNING;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; HUMANS; LEARNING; NEURAL NETWORKS (COMPUTER);

EID: 77951921295     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2010.2043445     Document Type: Article

References (19)

1. P.-A. Absil and K. A. Gallivan, "Joint diagonalization on the oblique manifold for independent component analysis," in Proc. IEEE Int. Conf. Acoust. Speech Signal Process., 2006, vol.5, pp. 945-948.
2. P.-A. Absil, R. Mahony, and R. Sepulchre, "Riemannian geometry of Grassmann manifolds with a view on algorithmic computation," Acta Applicandae Mathematicae, vol.80, no.2, pp. 199-220, Jan. 2004.
3. B. Afsari and P. S. Krishnaprasad, "Some gradient based joint diagonalization methods for ICA," in Proc. 5th Int. Conf. Ind. Compon. Anal. Blind Source Separat., 2004, pp. 437-444.
4. S.-I. Amari, "Natural gradient works efficiently in learning," Neural Comput., vol.10, pp. 251-276, 1998.
5. A. M. Bloch, P. E. Crouch, J. E. Marsden, and A. K. Sayal, "Optimal control and geodesics on quadratic matrix Lie groups," Found. Comput. Math., vol.8, pp. 469-500, 2008.
6. S. Fiori, "Quasi-geodesic neural learning algorithms over the orthogonal group: A tutorial," J. Mach. Learn. Res., vol.6, pp. 743-781, May 2005.
7. S. Fiori, "Lie-group-type neural system learning by manifold retractions," Neural Netw., vol.21, no.10, pp. 1524-1529, Dec. 2008.
8. S. Fiori, "Learning the Fréchet mean over the manifold of symmetric positive-definite matrices," Cogn. Comput., vol.1, no.4, pp. 279-291, Dec. 2009.
9. S. Fiori and T. Tanaka, "An algorithm to compute averages on matrix Lie groups," IEEE Trans. Signal Process., vol.57, no.12, pp. 4734-4743, Dec. 2009.
10. M. Fréchet, "Les élements aléatoires de nature quelconque dans un espace distancié," Annales de l'Institut Henri Poincaré, vol.10, pp. 215-310, 1948.
11. V. Guillemin and S. Sternberg, Symplectic Techniques in Physics. Cambridge, U.K.: Cambridge Univ. Press, 1984.
12. W. F. Harris, "Paraxial ray tracing through noncoaxial astigmatic optical systems, and a 5-5 augmented system matrix," Optom. Vis. Sci., vol.71, no.4, pp. 282-285, 1994.
13. D. G. Luenberger, "The gradient projection method along geodesics," Manage. Sci., vol.18, no.11, pp. 620-631, Jul. 1972.
14. B. Khesin and S. Tabachnikov, "Pseudo-Riemannian geodesics and billiards," Adv. Math., vol.221, no.4, pp. 1364-1396, Jul. 2009.
15. +(n,R) group manifold," Phys. Lett. A, vol.299, no.5-6, pp. 522-530, Jul. 2002.
16. A. Pambira, "Harmonic morphisms between degenerate semi-Riemannian manifolds," Beitra&Die;ge zur Algebra und Geometrie (Contributions to Algebra and Geometry), vol.46, no.1, pp. 261-281, 2005.
17. C. Small, The Statistical Theory of Shape.. Berlin, Germany: Springer-Verlag, 1996.
18. M. Spivak, A Comprehensive Introduction to Differential Geometry, 2nd ed. Berkeley, CA: Publish or Perish Press, 1979.
19. A. Yeredor, "Non-orthogonal joint diagonalization in the least-squares sense with application in blind source separation," IEEE Trans. Signal Process., vol.50, no.7, pp. 1545-1553, Jul. 2002.