We study a binary-cell-states eight-cell neighborhood two-dimensional cellular automaton model of a quasi-chemical system with a substrate and a reagent. Reactions are represented...
Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. They help ov...
In this paper, we propose the "Democratic Classifier", a simple, democracy-inspired patternbased classification algorithm that uses very short patterns for classificatio...
In this paper, we present a method for binary image comparison. For binary images, intensity information is poor and shape extraction is often difficult. Therefore binary images h...
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to...
Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Da...