Integrating defeasible argumentation with fuzzy ART neural networks for pattern classification

Abstract

Many classification systems rely on clustering techniques in which a collection of training examples is provided as an input, and a number of clusters c<SUB>1</SUB>,...c<SUB>m</SUB> modelling some concept C results as an output, such that every cluster c<SUB>i</SUB> is labelled as positive or negative. Given a new, unlabelled instance e<SUB>new</SUB>, the above classification is used to determine to which particular cluster c<SUB>i</SUB> this new instance belongs. In such a setting clusters can overlap, and a new unlabelled instance can be assigned to more than one cluster with conflicting labels. In the literature, such a case is usually solved non-deterministically by making a random choice. This paper presents a novel, hybrid approach to solve this situation by combining a neural network for classification along with a defeasible argumentation framework which models preference criteria for performing clustering.