Sciweavers

NIPS
2004

Sparse Coding of Natural Images Using an Overcomplete Set of Limited Capacity Units

14 years 26 days ago
Sparse Coding of Natural Images Using an Overcomplete Set of Limited Capacity Units
It has been suggested that the primary goal of the sensory system is to represent input in such a way as to reduce the high degree of redundancy. Given a noisy neural representation, however, solely reducing redundancy is not desirable, since redundancy is the only clue to reduce the effects of noise. Here we propose a model that best balances redundancy reduction and redundant representation. Like previous models, our model accounts for the localized and oriented structure of simple cells, but it also predicts a different organization for the population. With noisy, limited-capacity units, the optimal representation becomes an overcomplete, multi-scale representation, which, compared to previous models, is in closer agreement with physiological data. These results offer a new perspective on the expansion of the number of neurons from retina to V1 and provide a theoretical model of incorporating useful redundancy into efficient neural representations.
Eizaburo Doi, Michael S. Lewicki
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where NIPS
Authors Eizaburo Doi, Michael S. Lewicki
Comments (0)