Inductive learning from fuzzy examples

Abstract

In real applications, data provided to a learning system usually contain fuzzy information which greatly influences concept descriptions derived by conventional inductive learning methods. Modifying learning methods to learn concept descriptions in vague environments is thus very important. In this paper, we apply fuzzy set concept to machine learning to solve this problem. A fuzzy learning algorithm based on the version space strategy is proposed to manage fuzzy information. The proposed algorithm induces fuzzy linguistic inference rules from fuzzy instances, and finally infers outputs based on the fuzzy rules derived and user inputs. The Iris flower classification problem is used to compare the accuracy of the proposed algorithm with that of some other learning algorithms. Experimental results show that our method yields high accuracy.