Authorised by Academic Registrar, April 1996
Objectives On completion of the subject, students should understand the main current techniques used to implement machine learning; be able to design and implement a machine learning program; and appreciate the role of machine learning in AI theory and applications.
Synopsis This subject examines the main contending approaches taken to the computational modelling of learning. Topics include: production systems as cognitive models and their evolution into expert systems; version space approaches to concept formation; explanation-based learning; `scientific discovery' (data-driven) methods of learning empirical laws. The subject takes up various quantitative methods of learning, especially information-theoretic methods of classification and Bayesian learning techniques. Also covered: evolutionary programming (genetic algorithms) connectionism (neural networks), and the alleged incompatibilities between these different models.
Assessment Examination (2 hours): 50% + Programming project: 50%