The maximal causes of natural scenes are edge filters

Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010

Volumn , Issue , 2010, Pages

  Puertas, Gervasio ^a   Bornschein, Jörg ^a   Lücke, Jörg ^a  

^a FRANKFURT INSTITUTE FOR ADVANCED STUDIES   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

BANDPASS FILTERS; COMPUTER VISION; FUNCTIONS; IMAGE SEGMENTATION; MAXIMUM PRINCIPLE;

BASE FUNCTION; EDGE FILTERS; HIDDEN VARIABLE; IMAGE PATCHES; INDEPENDENT COMPONENTS ANALYSIS; LINEAR GENERATIVE MODEL; NATURAL SCENES; NON LINEAR; SPARSE CODING; SPARSE PRIOR;

INDEPENDENT COMPONENT ANALYSIS;

EID: 85162025802     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (35)

1. B. A. Olshausen, D. J. Field. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381:607-609, 1996.
2. P. Comon. Independent component analysis, a new concept? Signal Proc, 36(3):287-314, 1994.
3. A. J. Bell, T. J. Sejnowski. The "independent components" of natural scenes are edge filters. Vision Research, 37(23):3327-38, 1997.
4. A. Hyvärinen, E. Oja. A fast fixed-point algorithm for independent component analysis. Neural Computation, 9(7):1483-1492, 1997.
5. H. Lee, A. Battle, R. Raina, A. Ng. Efficient sparse coding algorithms. NIPS 22, 801-808, 2007.
6. M. W. Seeger. Bayesian Inference and Optimal Design for the Sparse Linear Model. Journal of Machine Learning Research, 759-813, 2008.
7. P. Dayan, L. F. Abbott. Theoretical Neuroscience. MIT Press, Cambridge, 2001.
8. P. Berkes, R. Turner, M. Sahani. On sparsity and overcompleteness in image models. NIPS 20, 2008.
9. B. A. Olshausen, K. J. Millman. Learning sparse codes with a mixture-of-Gaussians prior. NIPS 12, 841-847, 2000.
10. M. Rehn, F. T. Sommer. A network that uses few active neurones to code visual input predicts the diverse shapes of cortical receptive fields. J Comp Neurosci, 22(2):135-146, 2007.
11. A. Hyvärinen, P. Hoyer. Emergence of phase-and shift-invariant features by decomposition of natural images into independent feature subspaces. Neural Computation, 12(7):1705-1720, 2000.
12. F. Sinz, E. P. Simoncelli, M. Bethge. Hierarchical modeling of local image features through Lp-nested symmetric distributions. NIPS 22, 1696-1704, 2009.
13. D. Zoran, Y. Weiss. The "Tree-Dependent Components" of Natural Images are Edge Filters. NIPS 22, 2340-2348, 2009.
14. B. S. Everitt. An Introduction to Latent Variable Models. Chapman and Hall, 1984.
15. D. D. Lee, H. S. Seung. Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755):788-91, 1999.
16. P. Dayan, R. S. Zemel. Competition and multiple cause models. Neural Computation, 7:565-579, 1995.
17. E. Saund. A multiple cause mixture model for unsupervised learning. Neural Computation, 7:51-71, 1995.
18. H. Lappalainen, X. Giannakopoulos, A. Honkela, J. Karhunen. Nonlinear independent component analysis using ensemble learning: Experiments and discussion. Proc. ICA, 2000.
19. J. Lücke, M. Sahani. Maximal causes for non-linear component extraction. Journal of Machine Learning Research, 9:1227-1267, 2008.
20. N. Jojic, B. Frey. Learning flexible sprites in video layers. CVPR, 199-206, 2001.
21. N. Le Roux, N. Heess, J. Shotton, J.Winn. Learning a generative model of images by factoring appearance and shape. Technical Report, Microsoft Research, 2010.
22. R. Neal, G. Hinton. A view of the EM algorithm that justifies incremental, sparse, and other variants. M. I. Jordan, editor, Learning in Graphical Models. Kluwer, 1998.
23. J. Lücke, R. Turner, M. Sahani, M. Henniges. Occlusive Components Analysis. NIPS, 1069-1077, 2009.
24. P. O. Hoyer. Non-negative matrix factorization with sparseness constraints. Journal of Machine Learning Research, 5:1457-1469, 2004.
25. J. P. Jones, L. A. Palmer. An evaluation of the two-dimensional gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophysiology, 58(6):1233-1258, 1987.
26. P. Berkes, B.L. White, J. Fiser. No evidence for active sparsification in the visual cortex. NIPS 22, 2009.
27. J. Lücke. Receptive field self-organization in a model of the fine-structure in V1 cortical columns. Neural Computation, 21(10):2805-2845, 2009.
28. J. H. van Hateren, A. van der Schaaf. Independent component filters of natural images compared with simple cells in primary visual cortex. Proc Roy Soc London B, 265:359-366, 1998.
29. D. C. Somers, S. B. Nelson, M. Sur. An emergent model of orientation selectivity in cat visual cortical simple cells. The Journal of Neuroscience, 15:5448-5465, 1995.
30. J. Lücke. Learning of representations in a canonical model of cortical columns. Cosyne 2006, 100, 2006.
31. S. Osindero, M. Welling, G. E. Hinton. Topographic product models applied to natural scene statistics. Neural Computation, 18:381-414, 2006.
32. D. Arathorn, B. Olshausen, J. DiCarlo. Functional requirements of a visual theory. Workshop Cosyne. www.cosyne.org/c/index.php?title=Functional- requirements-of-a-visual-theory, 2007.
33. D. L. Ringach. Spatial structure and symmetry of simple-cell receptive fields in macaque primary visual cortex. Journal of Neurophysiology, 88:455-463, 2002. Data retrieved 2006 from manuelita.psych.ucla.edu/~dario.
34. B. A. Olshausen, D. J. Field. Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Research, 37(23):3311-3325, 1997.
35. S. Denéve, T. Lochmann, U. Ernst. Spike based inference in a network with divisive inhibition. Neural-Comp, Marseille, 2008.