Integrating defeasible argumentation with fuzzy ART neural networks for pattern classification
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&...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Articulo |
| Lenguaje: | Inglés |
| Publicado: |
2004
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/9479 http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Apr04-7.pdf |
| Aporte de: |
| Sumario: | 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. |
|---|