Detalle de artículo
Autores: Grinblat, G.L.; Granitto, P. M.; Ceccatto, H. A.
Resumen:
In this work we propose an adaptive classification method able both to learn and to follow the temporal evolution of a drifting concept. With that purpose we introduce a modified SVM classifier, created using multiple hyperplanes valid only at small temporal intervals (windows). In contrast to other strategies proposed in the literature, our method learns all hyperplanes in a global way, minimizing a cost function that evaluates the error committed by this family of local classifiers plus a measure associated to the VC dimension of the family. We also show how the idea of slowly changing classifiers can be applied to non-linear stationary concepts with results similar to those obtained with normal SVMs using gaussian kernels.
.Ubicación: INTELIGENCIA ARTIFICIAL. IBERO-AMERICAN JOURNAL OF ARTIFICIAL INTELLIGENCE.
Tipo de referato: Con Referato.
Está publicado?: Sí
ISSN: 1137-3601.
Volumen: 12.
Número: 40.
Páginas:39-50