Journal
NATURE
Volume 457, Issue 7225, Pages 83-U85Publisher
NATURE PUBLISHING GROUP
DOI: 10.1038/nature07481
Keywords
-
Categories
Funding
- Department of Energy
- Computational Science Graduate Fellowship
- National Science Foundation [0413152, 0705677]
- Office of Naval Research under the Multidisciplinary University Research Initiative [N000140710747]
Ask authors/readers for more resources
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(1,2), 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 cells(3-6) and offer insight into coding strategies in primary visual cortex (V1) and higher visual areas.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available