Abstract

In this paper we describe five paradigms for machine learning- connectionist (neural network) methods, genetic algorithms and classifier systems, empirical methods for inducing rules and decision trees, analytic learning methods, and case-based approaches. We consider some dimensions along which these paradigms vary in their approach to learning, and then review the basic methods used within each framework, together with open research issues. We will argue that the similarities among the paradigms are more important than their differences, and that future work should at-tempt to bridge the existing boundaries. Finally, we discuss some recent developments in the field of machine learning, and speculate on their impact for both research and applications.

Citations