A two-layer model of natural stimuli estimated with scorematching

Neural Computation

Volumn 22, Issue 9, 2010, Pages 2308-2333

  Köster, Urs ^a   Hyvärinen, Aapo ^b  

^a UNIVERSITY OF HELSINKI   (Finland)

^b HELSINKI INSTITUTE FOR INFORMATION TECHNOLOGY   (Finland)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; BIOLOGICAL MODEL; COMPUTER SIMULATION; LEARNING; LETTER; PHOTOSTIMULATION; PHYSIOLOGY; VISUAL CORTEX;

ALGORITHMS; COMPUTER SIMULATION; LEARNING; MODELS, NEUROLOGICAL; PHOTIC STIMULATION; VISUAL CORTEX;

EID: 78149334300     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/NECO_a_00010     Document Type: Letter

References (27)

1. Adelson, E., & Bergen, J. (1985). Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A, 2 284-299.
2. Barlow, H. (1961). Possible principles underlying the transformation of sensory messages. Cambridge, MA: MIT Press.
3. Comon, P. (1994). Independent component analysis-a new concept? Signal Processing, 36, 287-314.
4. Hinton, G. E. (2002). Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8), 1771-1800.
5. Hubel, D. H., & Wiesel, T. N. (1959). Receptive fields of single neurones in the cat's striate cortex. J. Physiol., 148, 574-591.
6. Hubel, D. H., & Wiesel, T. N. (1962). Receptive fields, binocular interaction and functional architecture in cat's visual cortex. J. Physiol., 160, 106-154.
7. Hyvärinen, A. (2005). Estimation of non-normalized statistical models using score matching. Journal of Machine Learning Research, 6, 695-709.
8. Hyvärinen,A. (2007a).Connections between scorematching, contrastive divergence, and pseudolikelihood for continuous-valued variables. IEEE Transactions on Neural Networks, 18(5), 1529-1531.
9. Hyvärinen, A. (2007b). Some extensions of score matching. Computational Statistics and Data Analysis, 51, 2499-2512.
10. Hyvärinen, A., Gutmann, M., & Hoyer, P. (2005). Statistical model of natural stimuli predicts edge-like pooling of spatial frequency channels in V2. BMC Neuroscience, 6(12).
11. Hyvärinen, A., & Hoyer, P. (2000). Emergence of phase and shift invariant features by decomposition of natural images into independent feature subspaces. Neural Computation, 12(7), 1705-1720.
12. Hyvärinen,A., &Hoyer, P.O. (2001). A two-layer sparse codingmodel learns simple and complex cell receptive fields and topography from natural images. Vision Research, 41, 2413-2423.
13. Hyvärinen, A., Hoyer, P., & Inki, M. (2001). Topographic independent component analysis. Neural Computation, 13(7), 1527-1558.
14. Hyvärinen, A., Hurri, J., & Hoyer, P. O. (2009). Natural image statistics. Berlin: Springer-Verlag.
15. Hyvärinen, A., & Köster, U. (2007). Complex cell pooling and the statistics of natural images. Network: Computation in Neural Systems, 18, 81-100.
16. Jutten, C., & Hérault, J. (1991). Blind separation of sources part I: An adaptive algorithm based on neuromimetic architecture. Signal Processing, 24, 1-10.
17. Karklin, Y., & Lewicki, M. S. (2005). A hierarchical Bayesian model for learning nonlinear statistical regularities in nonstationary natural signals. Neural Computation, 17(2), 397-423.
18. Karklin, Y., & Lewicki, M. S. (2006). Is early vision optimized for extracting higherorder dependencies? In Y. Weiss, B. Schölkopf, & J. Platt (Eds.), Advances in neural information processing systems, 18 (pp. 625-642). Cambridge, MA: MIT Press.
19. Köster, U., & Hyvärinen, A. (2007). A two-layer ICA-like model estimated by score matching. In Artificial Neural Networks-ICANN 2007, Lecture Notes in Computer Science (pp. 798-807). Berlin: Springer-Verlag.
20. Lindgren, J. T., & Hyvärinen, A. (2006). Emergence of conjunctive visual features by quadratic independent component analysis. In B. Schölkopf, J. Platt, & T. Hofmann (Eds.), Advances in neural information processing systems, 19 (pp. 897-904). Cambridge, MA: MIT Press.
21. Olshausen, B., & Field, D. (1996). Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381, 607-609.
22. Olshausen, B. A., & Field, D. J. (1997). Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Research, 37(23), 3311-3325.
23. Osindero, S., Welling, M., & Hinton, G. E. (2006). Topographic product models applied to natural scene statistics. Neural Computation, 18, 381-414.
24. Pollen, D., & Ronner, S. (1983). Visual cortical neurons as localized spatial frequency filters. IEEE Trans. on Systems, Man, and Cybernetics, 13, 907-916.
25. Schwartz, O., & Simoncelli, E. P. (2001). Natural signal statistics and sensory gain control. Nature Neuroscience, 4(8), 819-825.
26. Spitzer, H., & Hochstein, S. (1985). A complex-cell receptive-field model. J. Neurophysiol., 53, 1266-1286.
27. Vincent, B., Baddeley, R., Troscianko, T., & Gilchrist, I. (2005). Is the early visual system optimised to be energy efficient? Network, 16(2-3), 175-190.