Invariant recognition of feature combinations in the visual system

The operation of a hierarchical competitive network model (VisNet) of invariance learning in the visual system is investigated to determine how this class of architecture can solve problems that require the spatial binding of features. First, we show that VisNet neurons can be trained to provide transform-invariant discriminative responses to stimuli which are composed of the same basic alphabet of features, where no single stimulus contains a unique feature not shared by any other stimulus. The investigation shows that the network can discriminate stimuli consisting of sets of features which are subsets or supersets of each other. Second, a key feature-binding issue we address is how invariant representations of low-order combinations of features in the early layers of the visual system are able to uniquely specify the correct spatial arrangement of features in the overall stimulus and ensure correct stimulus identi

• Type: Journal
• Year: 2002
• Where: BC
• Authors: Martin C. M. Elliffe, Edmund T. Rolls, Simon M. Stringer
• Keywords: BC 2002, Hierarchical Competitive Network, Output Layer, Transform-invariant Discriminative Responses