Advanced search


Ramón A. Mollineda, Enrique Vidal, Carlos D. Martínez-Hinarejos. Adaptive Learning for String Classification. 1st Iberian Conference on Pattern Recognition and Image Analysis, 2003. Francisco J. Perales, Aurélio J.C. Campilho, Nicolás Pérez de la Blanca, Alberto Sanfeliu (Editors). pp. 564-571. Springer-Verlag.

A new LVQ-inspired adaptive method is introduced to optimize strings for the 1-NN classifier. The updating rule relies on the edit distance. Given an initial number of string prototypes and a training set, the algorithm builds supervised clusters by attaching training samples to prototypes. A prototype is then rewarded to get it closer to the members of its cluster. To this end, the prototype is updated according to the most frequent edit operations resulting from edit distance computations to all members of its cluster. The process reorganizes training samples into new clusters and continues until the convergence of prototypes is achieved. A series of learning/classification experiments is presented which show a better 1-NN performance of the new prototypes with respect to the initial ones, that were originally good for classification.