Nature Publishing Group, publisher of Nature, and other science journals and reference works
Nature
my account e-alerts subscribe register
   
Sunday 25 June 2017
Journal Home
Current Issue
AOP
Archive
Download PDF
References
Export citation
Export references
Send to a friend
More articles like this

Letters to Nature
Nature 381, 607 - 609 (13 June 1996); doi:10.1038/381607a0

Emergence of simple-cell receptive field properties by learning a sparse code for natural images

Bruno A. Olshausen* & David J. Field

Department of Psychology, Uris Hall, Cornell University, Ithaca, New York 14853, USA
*Present address: Center for Neuroscience, UC Davis, Davis, California 95616, USA.

THE receptive fields of simple cells in mammalian primary visual cortex can be characterized as being spatially localized, oriented1–4 and bandpass (selective to structure at different spatial scales), comparable to the basis functions of wavelet transforms5,6. One approach to understanding such response properties of visual neurons has been to consider their relationship to the statistical structure of natural images in terms of efficient coding7–12. Along these lines, a number of studies have attempted to train unsupervised learning algorithms on natural images in the hope of developing receptive fields with similar properties13–18, but none has succeeded in producing a full set that spans the image space and contains all three of the above properties. Here we investigate the proposal8,12 that a coding strategy that maximizes sparseness is sufficient to account for these properties. We show that a learning algorithm that attempts to find sparse linear codes for natural scenes will develop a complete family of localized, oriented, bandpass receptive fields, similar to those found in the primary visual cortex. The resulting sparse image code provides a more efficient representation for later stages of processing because it possesses a higher degree of statistical independence among its outputs.

------------------

References

1. Hubel, D. H. & Wiesel, T. N. J. Physiol., Lond. 195, 215−244 (1968). | PubMed | ISI | ChemPort |
2. De Valois, R. L., Albrecht, D. G. & Thorell, L. G. Vision Res. 22, 545−559 (1982). | Article | PubMed | ISI | ChemPort |
3. Jones, J. P. & Palmer, L. A. J. Neurophysiol. 58, 1233−1258 (1987). | PubMed | ISI | ChemPort |
4. Parker, A. J. & Hawken, M. J. J. opt. Soc. Am. A 5, 598−605 (1988). | ChemPort |
5. Daugman, J. G. Computational Neuroscience (ed. Schwartz, E.) 403−423 (MIT Press, Cambridge, MA, 1990).
6. Field, D. J. in Wavelets, Fractals, and Fourier Transforms (eds Farge, M., Hunt, J. & Vascillicos, C.) 151−193 (Oxford Univ. Press, 1993).
7. Srinivasan, M. V., Laughlin, S. B. & Dubs, A. Proc. R. Soc. Lond. B216, 427−459 (1982). | ChemPort |
8. Field, D. J. J. opt. Soc. Am. A4, 2379−2394 (1987). | ChemPort |
9. Atick, J. J. Network 3, 213−251 (1992). | Article | ISI |
10. van Hateren, J. H. Nature 360, 68−70 (1992). | Article | PubMed | ChemPort |
11. Ruderman, D. L. Network 5, 517−548 (1994).
12. Field, D. J. Neur. Comput. 6, 559−601 (1994).
13. Barrow, H. G. in IEEE First Int. Conf. on Neural Networks Vol. 4, (eds Caudill, M. & Butler, C.) 115−121 (Institute of Electrical and Electronics Engineers, 1994).
14. Sanger, T. D. in Advances in Neural Information Processing Systems Vol. I (ed. Touretzky, D.) 11−19 (Morgan-Kaufmann, 1989).
15. Hancock, P. J. B., Baddeley, R. J. & Smith, L. S. Network 3, 61−72 (1992).
16. Law, C. C. & Cooper, L. N. Proc. natn. Acad. Sci. U.S.A. 91, 7797−7801 (1994). | ChemPort |
17. Fyfe, C. & Baddeley, R. Network 6, 333−344 (1995).
18. Schmidhuber, J., Eldracher, M. & Foltin, B. Neur. Comput. 8 773−786 (1996).
19. Barlow, H. B. Neur. Comput. 1, 295−311 (1989).
20. Linsker, R. Computer 105−117 (March, 1988).
21. Olshausen, B. A. & Field, D. J. Network 7, 333−339 (1996).
22. Daugman, J. G. IEEE Trans. biomed. Engng. 36, 107−114 (1989). | Article | ChemPort |
23. Harpur, G. F. & Prager, R. W. Network 7, 277−284 (1996).
24. Foldiak, P. Biol. Cybernet. 64, 165−170 (1990). | ChemPort |
25. Zemel, R. S. thesis, Univ. Toronto (1993).
26. Intrator, N. Neur. Comput. 4, 98−107 (1992).
27. Bell, A. J. & Sejnowski, T. J. Neur. Comput. 7, 1129−1159 (1995). | ChemPort |
28. Saund, E. Neur. Comput. 7, 51−71 (1995).
29. Hinton, G. E., Dayan, P., Frey, B. J. & Neal, R. M. Science 268, 1158−1161 (1995). | PubMed | ISI | ChemPort |
30. Lu, Z. L., Chubb, C. & Sperling, G. Technical Report MBS 96-15 (Institute for Mathematical Behavioral Sciences, University of California at Irvine, 1996).



© 1996 Nature Publishing Group
Privacy Policy