Hostname: page-component-7c8c6479df-r7xzm Total loading time: 0 Render date: 2024-03-27T07:52:30.377Z Has data issue: false hasContentIssue false

Sparse coding and challenges for Bayesian models of the brain

Published online by Cambridge University Press:  10 May 2013

Thomas Trappenberg
Affiliation:
Faculty of Computer Science, Dalhousie University, Halifax, NS B3H 4R2, Canada. tt@cs.dal.capaulhollensen@gmail.comwww.cs.dal.ca/~tt
Paul Hollensen
Affiliation:
Faculty of Computer Science, Dalhousie University, Halifax, NS B3H 4R2, Canada. tt@cs.dal.capaulhollensen@gmail.comwww.cs.dal.ca/~tt

Abstract

While the target article provides a glowing account for the excitement in the field, we stress that hierarchical predictive learning in the brain requires sparseness of the representation. We also question the relation between Bayesian cognitive processes and hierarchical generative models as discussed by the target article.

Type
Open Peer Commentary
Copyright
Copyright © Cambridge University Press 2013 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Barlow, H. B. (1961) Possible principles underlying the transformations of sensory messages. In: Sensory communication, ed. Rosenblith, W., pp. 217–34. (Chapter 13). MIT Press.Google Scholar
Földiák, P. (1990) Forming sparse representations by local anti-Hebbian learning. Biological Cybernetics 64:165–70.CrossRefGoogle ScholarPubMed
Friston, K. J. (2010) The free-energy principle: A unified brain theory? Nature Reviews Neuroscience 11(2):127–38.CrossRefGoogle ScholarPubMed
Hollensen, P. & Trappenberg, T. (2011) Learning sparse representations through learned inhibition. Poster presented at the COSYNE (Computational and Systems Neuroscience Conference) Annual Meeting, Salt Lake City, Utah, February 24, 2011.Google Scholar
Jaeger, H. (2011) Neural hierarchies: Singin' the blues. Oral presentation at Osnabrück Computational Cognition Alliance Meeting (OCCAM 2011), University of Osnabrück, Germany, June 22–24, 2011. Available at: http://video.virtuos.uni-osnabrueck.de:8080/engage/ui/watch.html?id=10bc55e8-8d98-40d3-bb11-17780b70c052&play=true.Google Scholar
Lee, H., Ekanadham, C. & Ng, A. (2008) Sparse deep belief net model for visual area V2. In: Advances in Neural Information Processing Systems 20 (NIPS'07), ed. Platt, J., Koller, D., Singer, Y. & Roweis, S., pp. 873–80. MIT Press.Google Scholar
Olshausen, B. A. & Field, D. J. (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583):607609.CrossRefGoogle ScholarPubMed
Rust, N. C., Schwartz, O., Movshon, J. A. & Simoncelli, E. P. (2005) Spatiotemporal elements of Macaque V1 receptive fields. Neuron 46:945–56.CrossRefGoogle ScholarPubMed
Saxe, A., Bhand, M., Mudur, R., Suresh, B. & Ng, A. (2011) Modeling cortical representational plasticity with unsupervised feature learning. Poster presented at COSYNE 2011, Salt Lake City, Utah, February 24–27, 2011. Available at: http://www.stanford.edu/~asaxe/papers.Google Scholar
Vinje, W. E. & Gallant, J. L. (2000) Sparse coding and decorrelation in primary visual cortex during natural vision. Science 287:1273–76.Google Scholar
Waydo, S., Kraskov, A., Quiroga, R. Q., Fried, I. & Koch, C. (2006) Sparse representation in the human medial temporal lobe. Journal of Neuroscience 26:10232–34.CrossRefGoogle ScholarPubMed