Nature 457, 83-86 (1 January 2009) | doi:10.1038/nature07481; Received 4 May 2008; Accepted 26 September 2008; Published online 19 November 2008

Emergence of complex cell properties by learning to generalize in natural scenes

Yan Karklin1,2 & Michael S. Lewicki1,2

  1. Computer Science Department & Center for the Neural Basis of Cognition, Carnegie Mellon University, Pittsburgh, PA 15213, USA
  2. Present address: Center for Neural Science, New York University, New York, New York, USA (Y.K.); Electrical Engineering and Computer Science Department, Case Western University, Cleveland, Ohio, USA and Wissenschaftskolleg (Institute for Advanced Study) zu Berlin, Germany (M.S.L.).

Correspondence to: Yan Karklin1,2Michael S. Lewicki1,2 Correspondence and requests for materials should be addressed to Y.K. (Email: yan.karklin@nyu.edu) or M.S.L. (Email: michael.lewicki@case.edu).

A fundamental function of the visual system is to encode the building blocks of natural scenes—edges, textures and shapes—that subserve visual tasks such as object recognition and scene understanding. Essential to this process is the formation of abstract representations that generalize from specific instances of visual input. A common view holds that neurons in the early visual system signal conjunctions of image features1, 2, but how these produce invariant representations is poorly understood. Here we propose that to generalize over similar images, higher-level visual neurons encode statistical variations that characterize local image regions. We present a model in which neural activity encodes the probability distribution most consistent with a given image. Trained on natural images, the model generalizes by learning a compact set of dictionary elements for image distributions typically encountered in natural scenes. Model neurons show a diverse range of properties observed in cortical cells. These results provide a new functional explanation for nonlinear effects in complex cells3, 4, 5, 6 and offer insight into coding strategies in primary visual cortex (V1) and higher visual areas.


These links to content published by NPG are automatically generated.


A natural approach to studying vision

Nature Neuroscience Perspective (01 Dec 2005)

See all 14 matches for Reviews


Color in the cortex revisited

Nature Neuroscience News and Views (01 Apr 2001)

Learning from your neighbour

Nature News and Views (09 Jan 1992)

See all 5 matches for News And Views


Surrogate Endpoints for the Treatment of Venous Leg Ulcers

Journal of Investigative Dermatology Original Article

What constitutes an efficient reference frame for vision?

Nature Neuroscience Article (01 Oct 2002)

See all 78 matches for Research