From biological vision to unsupervised hierarchical sparse coding
This work addresses the challenge of understanding biological vision mechanisms for neuroscience and AI researchers, but it is incremental as it replicates an existing algorithm in a biological context.
The paper tackled the problem of modeling the unsupervised development of feature-selective cells in the primary visual cortex, proposing a biological model using the Multi-Layer Convolutional Sparse Coding algorithm to replicate this process.
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.