A multi-layer sparse coding network learns contour coding from natural images

An important approach in visual neuroscience considers how the function of the early visual system relates to the statistics of its natural input. Previous studies have shown how many basic properties of the primary visual cortex, such as the receptive fields of simple and complex cells and the spat...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Vision research (Oxford) Ročník 42; číslo 12; s. 1593 - 1605
Hlavní autoři: Hoyer, Patrik O, Hyvärinen, Aapo
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford Elsevier Ltd 01.06.2002
Elsevier Science
Témata:
Biological and medical sciences
Cerebral Cortex - physiology
Contours
Cortex
Fundamental and applied biological sciences. Psychology
Humans
Independent component analysis
Models, Neurological
Natural images
Nerve Net
Neural networks
Neurophysiology
Perception
Psychology. Psychoanalysis. Psychiatry
Psychology. Psychophysiology
Vision
Vision, Ocular - physiology
Neural networks
Contours
Cortex
Independent component analysis
Natural images
Learning
Visual cortex
Coding
Contour
Vision
Central nervous system
Perception
Simulation model
Neural network
Mathematical model
Brain (vertebrata)
ISSN:0042-6989, 1878-5646
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:An important approach in visual neuroscience considers how the function of the early visual system relates to the statistics of its natural input. Previous studies have shown how many basic properties of the primary visual cortex, such as the receptive fields of simple and complex cells and the spatial organization (topography) of the cells, can be understood as efficient coding of natural images. Here we extend the framework by considering how the responses of complex cells could be sparsely represented by a higher-order neural layer. This leads to contour coding and end-stopped receptive fields. In addition, contour integration could be interpreted as top-down inference in the presented model.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0042-6989
1878-5646
DOI:10.1016/S0042-6989(02)00017-2