A Vision Architecture

TL;DR

This paper proposes a neural connectivity and dynamics interpretation as a data-and-process architecture for the visual system, emphasizing structured networks formed through learning and their role in perception.

Contribution

It introduces a novel interpretation of cortical connectivity as hierarchically structured networks formed by learning, explaining visual processing and invariance.

Findings

Networks are formed on slow time-scale by learning.

Hierarchical networks represent visual structure.

Networks facilitate invariant perception.

Abstract

We are offering a particular interpretation (well within the range of experimentally and theoretically accepted notions) of neural connectivity and dynamics and discuss it as the data-and-process architecture of the visual system. In this interpretation the permanent connectivity of cortex is an overlay of well-structured networks, nets, which are formed on the slow time-scale of learning by self-interaction of the network under the influence of sensory input, and which are selectively activated on the fast perceptual time-scale. Nets serve as an explicit, hierarchically structured representation of visual structure in the various sub-modalities, as constraint networks favouring mutually consistent sets of latent variables and as projection mappings to deal with invariance.