A theory and methodology of inductive learning

• Published in: Artificial intelligence Vol. 20; no. 2; pp. 111 - 161
• Main Author: Michalski, Ryszard S.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.1983
• ISSN: 0004-3702; 1872-7921
• DOI: 10.1016/0004-3702(83)90016-4

A theory of inductive learning is presented that characterizes it as a heuristic search through a space of symbolic descriptions, generated by an application of certain inference rules to the initial observational statements (the teacher-provided examples of some concepts, or facts about a class of objects or a phenomenon). The inference rules include generalization rules, which perform generalizing transformations on descriptions, and conventional truth-preserving deductive rules (specialization and reformulation rules). The application of the inference rules to descriptions is constrained by problem background knowledge, and guided by criteria evaluating the ‘quality’ of generated inductive assertions. Based on this theory, a general methodology for learning structural descriptions from examples, called star, is described and illustrated by a problem from the area of conceptual data analysis.