Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published May 2008 | Published
Journal Article Open

Unsupervised Learning of Individuals and Categories from Images

Abstract

Motivated by the existence of highly selective, sparsely firing cells observed in the human medial temporal lobe (MTL), we present an unsupervised method for learning and recognizing object categories from unlabeled images. In our model, a network of nonlinear neurons learns a sparse representation of its inputs through an unsupervised expectation-maximization process. We show that the application of this strategy to an invariant feature-based description of natural images leads to the development of units displaying sparse, invariant selectivity for particular individuals or image categories much like those observed in the MTL data.

Additional Information

© 2008 The MIT Press. Received March 20, 2007; accepted July 16, 2007. This work was supported by grants from NIMH, NSF, ONR, DARPA, the Mathers Foundation, and a Fannie and John Hertz Foundation fellowship to S.W. Thomas Serre and Minjoon Kouh of MIT provided invaluable assistance in the setup and operation of the underlying vision model.We thank Richard Murray, Pietro Perona, Jerry Marsden, Tomoso Poggio, Bruno Olshausen, and the members of klab for valuable comments on this work.

Attached Files

Published - WAYnc08b.pdf

Files

WAYnc08b.pdf
Files (3.3 MB)
Name Size Download all
md5:253d8a67794e7aa531c92f2afcbb8d47
3.3 MB Preview Download

Additional details

Created:
September 14, 2023
Modified:
October 23, 2023