Natural gradient learning for over- and under-complete bases in ICA

Neural Computation

Volumn 11, Issue 8, 1999, Pages 1875-1883

  Amari, Shun Ichi ^a  

^a RIKEN BRAIN SCIENCE INSTITUTE   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; BIOLOGICAL MODEL; LEARNING; PHYSIOLOGY;

LEARNING; MODELS, NEUROLOGICAL;

EID: 0033570817     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976699300015990     Document Type: Article

References (14)

1. Amari, S. (1998). Natural gradient works efficiently in learning. Neural Computation, 10, 251-276.
2. Amari, S., Chen, T.-P., & Cichocki, A. (1997). Stability analysis of adaptive blind source separation. Neural Networks, 10, 1345-1351.
3. Amari, S., Cichocki, A., & Yang, H. (1996). A new learning algorithm for blind signal separation. In D. S. Touretzky, C. M. Mozer, & M. E. Hasselmo (Eds.), Advances in neural information processing systems, 8 (pp. 757-763). Cambridge, MA: MIT Press.
4. Bell, A. J., & Sejnowski, T. J. (1995). An information-maximization approach to blind separation and blind deconvolution. Neural Computation, 7, 1129-1159.
5. Cardoso, J. F., & Laheld, B. (1996). Equivariant adaptive source separation. IEEE Trans, on Signal Processing, 44, 3017-3030.
6. Chen, S., Donoho, D. L., & Saunders, M. A. (1996). Atomic decomposition by basis pursuit (Tech. Rep.). Stanford: Stanford University.
7. Cichocki, A., Thawonmas, R., & Amari, S. (1997). Sequential blind signal extraction in order specified by stochastic properties. Electronics Letters, 33, 64-65.
8. Comon, P. (1994). Independent component analysis, a new concept? Signal Processing, 36, 287-314.
9. Edelman, A., Arias, T., & Smith, S. T. (1998). The geometry of algorithms with orthogonality constraints. SIAM Journal of Matrix Analysis and Applications, 20, 303-353.
10. Girosi, F. (1998). An equivalence between sparse approximation and support vector machines. Neural Computation, 10, 1455-1480.
11. Jutten, C., & Herault, J. (1991). Blind separation of sources, Part I: An adaptive algorithm based on neuromimetic architecture. Signal Processing, 24, 1-20.
12. Lewicki, M. S., & Sejnowski, T. (1998a). Learning nonlinear overcomplete representations for efficient coding. In M. Kearns, M. Jordan, & S. Solla (Eds.), Advances in neural information processing systems, 10 (pp. 556-562). Cambridge, MA: MIT Press.
13. Lewicki, M. S., & Sejnowski, T. (1998b). Learning overcomplete representations. Unpublished manuscript, Salk Institute.
14. Yang, H. H., & Amari, S. (1997). Adaptive online learning algorithms for blind separation: Maximum entropy and minimal mutual information. Neural Computation, 9, 1457-1482.