Synthesis of Decision Rules for Object Classification
Jan G. Bazan, Hung Son Nguyen, Tuan Trung Nguyen, Andrzej Skowron, Jarosław Stepaniuk · Studies in fuzziness and soft computing · 1998
We discuss two applications of logic to the problem of object classification. The first is related to an application of multi-modal logics to the automatic feature extraction. The second is concerned with inductive reasoning for discovering an optimal feature set with respect to the precision of classification and for improving the performance of decision algorithms. We also present an exemplary system for recognizing handwritten digits based on Boolean reasoning, rough set methods and feature discovery by applying multi-modal logic. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.