Integrating defeasible argumentation with fuzzy ART neural networks for pattern classification

• Autores: Gómez, Sergio Alejandro; Chesñevar, Carlos Iván
• Año de publicación: 2004
• Idioma: inglés
• Tipo de recurso: artículo
• Materia: Ciencias Informáticas; clasificación; Neural nets; Patterns (e.g., client/server, pipeline, blackboard); machine learning
• Institución: Universidad Nacional de La Plata

Many classification systems rely on clustering techniques in which a collection of training examples is provided as an input, and a number of clusters c₁,...c_m modelling some concept C results as an output, such that every cluster c_i is labelled as positive or negative. Given a new, unlabelled instance e_new, the above classification is used to determine to which particular cluster c_i 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.
Facultad de Informática