Some Philosophical Problems with Formal Learning Theory

Jonathan Amsterdam

Recent work in formal learning theory has attempted to capture the essentials of the concept-learning task in a formal framework. This paper evaluates the potential contributions of certain kinds of models to the study of learning by exploring the philosophical implications of these models. Some of my remarks bear on mainstream AI learning techniques such as version spaces and explanation-based learning.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.