Work

From biological vision to unsupervised hierarchical sparse coding

Year: 2018

Type: preprint

Abstract: The formation of connections between neural cells is emerging essentially from an unsupervised learning process. For instance, during the development of the primary visual cortex of mammals (V1), we observe the emergence of cells selective to localized and oriented features. This leads to the development of a rough contour-based representation of the retinal image in area V1. We propose a biological model of the formation of this representation along the thalamo-cortical pathway. To achieve this goal, we replicated the Multi-Layer Convolutional Sparse Coding (ML-CSC) algorithm developed by Michael Elad's group.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1812.01335

Authors: Boutin, Victor, Franciosini, Angelo, Ruffier, Franck, Perrinet, Laurent. U

Institutions: Centre National de la Recherche Scientifique, Aix-Marseille Université, Institut de Neurosciences de la Timone, Institut des Sciences du Mouvement Etienne-Jules Marey

Language: English

Topic: Visual perception and processing mechanisms

Subfield: Cognitive Neuroscience

Field: Neuroscience

Domain: Life Sciences

Open Access status: green

Funders: European Commission, Agence Nationale de la Recherche, Horizon 2020 Framework Programme

Awards: INITIATIVE D'EXCELLENCE AIX MARSEILLE UNIVERSITE, G1742243815, International, inter-sectoral and inter-disciplinary Doctoral Training Programme to Aix-Marseille University, G4866930200, G582846875, G746376862, G782245399

OpenAlex ID: W2903405877

Cites: 9

Cited by:

Related to: 20