Sparse coding of time-varying natural images | Zendy

Bruno A. Olshausen | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Sparse coding of time-varying natural images

Author(s) -

Bruno A. Olshausen

Publication year - 2010

Publication title -

journal of vision

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 1.126

H-Index - 113

ISSN - 1534-7362

DOI - 10.1167/2.7.130

Subject(s) - receptive field , neural coding , superposition principle , computer science , basis function , basis (linear algebra) , artificial intelligence , coding (social sciences) , pattern recognition (psychology) , algorithm , mathematics , mathematical analysis , statistics , geometry

We show how the principle of sparse coding may beapplied to learn the forms of structure occurring intime-varying natural images. A sequence of images isdescribed as a linear superposition of space-time functions,each of which is convolved with a time-varyingcoefficient signal. When a sparse, independent representationis sought over the coefficients, the basis functionsthat emerge are space-time inseparable functionsthat resemble the motion-selective receptive fields ofcortical simple...

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research