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

Yan Karklin () and Michael S. Lewicki ()
Additional contact information
Yan Karklin: Carnegie Mellon University, Pittsburgh, PA 15213, USA
Michael S. Lewicki: Carnegie Mellon University, Pittsburgh, PA 15213, USA

Nature, 2009, vol. 457, issue 7225, 83-86

Abstract: Building the picture Complex visual scenes are made up of many component features such as edges and textures. Neurons in the early stages of the visual system are sensitive to individual features; it's implicitly believed that the nervous system must put them back together to signal conjunctions of different features, but how this is achieved is unknown. Yan Karklin and Michael Lewicki have developed a computational model of visual processing in which neural activity encodes statistical variations of features in images, establishing which ones are most likely to be associated with each other. Aspects of the model echo the nonlinear properties of some visual neurons, hinting at a possible functional interpretation for these properties.

Date: 2009
References: Add references at CitEc
Citations: View citations in EconPapers (7)

Downloads: (external link)
https://www.nature.com/articles/nature07481 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:457:y:2009:i:7225:d:10.1038_nature07481

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/nature07481

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().