Format

Send to

Choose Destination
Nature. 2009 Jan 1;457(7225):83-6. doi: 10.1038/nature07481. Epub 2008 Nov 19.

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

Author information

1
Computer Science Department & Center for the Neural Basis of Cognition, Carnegie Mellon University, Pittsburgh, PA 15213, USA. yan.karklin@nyu.edu

Abstract

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 features, 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 cells and offer insight into coding strategies in primary visual cortex (V1) and higher visual areas.

PMID:
19020501
DOI:
10.1038/nature07481
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center