|Assessment Type||Assessment length / details||Proportion|
|Semester Exam||2 Hours||100%|
|Supplementary Exam||Supplementary examination will take the same form, under the terms of the Department's policy.|
On completion of this module, students should be able to:
- identify the main application areas in which artificial intelligence has been applied;
- discuss some of the main controversies within and around artificial intelligence, particularly those concerning the nature of intelligence, and the limits of artificial intelligence;
- explain the contributions of artificial intelligence to computing in general, and to industry and commerce, particularly in the area of expert systems;
- describe and assess artificial intelligence techniques for a selected set of application topics;
- make intelligent use of artificial intelligence software.
This module concentrates on the technology and methodology of artificial intelligence (AI) practice. The aim is to show how practical knowledge-based systems can be implemented, developed and evaluated.
This course aims to give students a good understanding of a variety of AI systems, from expert systems through machine learning to adaptive computing. This will enable them to appreciate what current AI systems can and cannot do, and the circumstances in which their use is appropriate.
What is AI? Introduction to the range of applications of AI. Why do we need AI and how do we use it?
2. Intelligent Agents
How can we build an intelligent robot? Sensing, Action and Cognition. The symbolic approach. Memory, representation and reasoning.
3. Machine Vision
How can robots see? The nature of the vision task. Computer vision and image processing.
How can robots think? Knowledge representation methods. Reasoning and inference.
5. Expert Systems
How can human expertise be automated? Example applications and commercial successes. How to build an expert system - system concepts and architectures. Rule-based systems: design, operation and worked examples. Knowledge bases and knowledge based systems.
6. Artificial Brains
How can robot brains be built? Artificial neural nets, pattern recognition and learning.
7. Search and reasoning
Why do we need search? Evaluation of search strategies. Un-informed search techniques. Informed search techniques.
8. Machine Learning
How can a computer program learn? Inductive learning. Structural methods. Genetic algorithms.
9. Learning application
Case-based reasoning. Data mining.
Reading ListRecommended Text
Alison Cawsey (1998) The Essence of Artificial Intelligence Essence of Computing Series. Prentice Hall Primo search S.J. Russell and P. Norvig (1995) AI: A Modern Approach Prentice-Hall Primo search Consult For Futher Information
E. Rich and K. Knight (1991) Artificial Intelligence 2nd McGraw Hill Primo search J. Giarratano and G. Riley (1998) Expert Systems: Principles and programming Boston PWS Primo search
This module is at CQFW Level 7