MIN-MAX CLASSIFIERS - LEARNABILITY, DESIGN AND APPLICATION

PATTERN RECOGNITION

卷:28

Article

YANG, PF ; MARAGOS, P

关键词: PATTERN CLASSIFICATION;    MACHINE LEARNING;    MATHEMATICAL MORPHOLOGY;    IMAGE PROCESSING;    CHARACTER RECOGNITION;   

DOI  :  10.1016/0031-3203(94)00161-E

来源: Elsevier

【 摘 要 】

This paper introduces the class of min-max classifiers. These are binary-valued functions that can be used as pattern classifiers of both real-valued and binary-valued feature vectors. They are also lattice-theoretic generalization of Boolean functions and are also related to feed-forward neural networks and morphological signal operators. We studied supervised learning of these classifiers under the Probably Approximately Correct (PAC) model proposed by Valiant. Several subclasses of thresholded min-max functions are shown to be learnable, generalizing the learnability results for the corresponding classes of Boolean functions. We also propose a LMS algorithm for the practical training of these pattern classifiers. Experimental results using the LMS algorithm for handwritten character recognition are promising. For example, in our experiments the min-max classifiers were able to achieve error rates that are comparable or better than those generated using neural networks. The major advantage of min-max classifiers compared to neural networks is their simplicity and the faster convergence of their training algorithm.

【 授权许可】

Free