A fuzzy inductive learning strategy for modular rules

In real applications, data provided to a learning system usually contain li nguistic information which greatly influences concept descriptions derived by conventional inductive learning methods. The design of learning methods to learn concept descriptions in working with vague data is thus very impor tant. In this paper, we apply fuzzy set concepts to machine learning to sol ve this problem. A fuzzy learning algorithm based on the maximum informatio n gain is proposed to manage linguistic information. The proposed learning algorithm generates fuzzy rules from "soft" instances, which differ from co nventional instances in that they have class membership values. Experiments on the Sports and the Iris Flower classification problems are presented to compare the accuracy of the proposed algorithm with those of some other le arning algorithms. Experimental results show that the rules derived from ou r approach are simpler and yield higher accuracy than those from some other learning algorithms. (C) 1999 Elsevier Science B.V. All rights reserved.