Not offered in 2005.
Synopsis: Contending approaches to the computational modelling of learning, the applications to which they are suited and their growing use in 'mining' the data in very large corporate and governmental databases. Topics include the need for extracting patterns from databases to support business decision making; the nature of learning and its computational modelling; symbolic approaches to machine learning; scientific discovery; information-theoretic classification; Bayesian learning; minimum encoding methods; evolutionary methods and artificial life; neural networks.
Assessment: Examination (3 hours): 50% + Programming project: 50%
Contact Hours: Two 1-hour lectures per week