Ongoing learning for supervised pattern recognition

Barandela. R.M. Juarez

This paper presents a procedure to implement an automatic system for supervised pattern recognition with an ongoing learning capability. The purpose is to continuously increase the knowledge of the system and, accordingly, to enhance its performance in classification tasks.The Nearest Neighbor rule is employed as the central classifier and several techniques are added to cope with the increase in computational load and with the peril of incorporating noisy data to the training sample. Experimental results confirm the improvement in classification accuracy.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: