This module builds on CS26210 and examines some of the key ideas in Artificial Intelligence. A small number of topics are studied in depth in order to give insight and understanding of the methods and issues involved in state-of-the-art developments.
The primary aim of this module is to give students a deeper understanding of some of the principle concepts of artificial intelligence, developed in the Artificial Intelligence Concepts module CS26210 . In concentrating on model-based reasoning (MBR) and machine learning, this module will make full use of the expertise and research strengths of members of the lecturing staff.
On successful completion of this module students should be able to:
appreciate the range of applicability of MBR;
explain the state of the art of MBR;
describe the operation of a qualitative reasonong (QR) system;
describe the problem of spurious behaviour generation and describe some research solutions to it;
have sufficient knowledge of a basic rule induction method, such as ID3, to be able to explain it;
explain the theory behind artificial neural networks, in particular back propagation and Kohonen nets;
describe and explain the theory behind concept learning;
compare and contrast theories of genetic algorithms and genetic programming.
Model Based Reasoning
1. Introduction to Model-based reasoning and its applications - 1 lecture
2. Basic concepts in MBR - 3 lectures
Qualitative arithmetic, quantity spaces, model-types, ontologies.
3. Introduction to Qualitative Simulation - 2 lectures
Mycroft and QSIM.
4. Problems and Solutions - 1 lecture
Spurious behaviour generation and some spcific solutions.
5. Example and Revisions - 1 lecture
Machine Learning - 12 Lectures
** Recommended Text
T. Mitchell. (1997)
Machine Learning. McGraw Hill 0070428077
** Consult For Futher Information
B.J. Kuipers. (1994)
Qualitative Reasoning: modelling and simulation with incomplete knowledge. MIT Press 026211190X
S. M. Weiss and C. A. Kulikowsky. (1991)
Computer Systems That Learn. Morgan Kaufmann 1558600655