Computer Science, Prifysgol Cymru Aberystwyth University of Wales

CS36310 (1995-96 session)
Artificial Intelligence Systems

Brief Description

Aims, Objectives, Syllabus, Booklist

Further Details

Number of lectures

12

Number of seminars/tutorials

6

Number of practicals

6 x 1-hour

Coordinator

Dr. Fred Long

Other staff involved

Not yet known

Pre-requisites

CS36210

Co-requisites

None

Incompatibilities

None

Assessment

Assessed coursework - 20%
Written exam - 80%

Timing

This module is offered only in Semester 2

This course will provide a good understanding of a variety of AI systems from machine learning through adaptive computing to expert systems. This will enable students to gain an understanding of the current state of the art AI systems.

The emphasis on the course will be in not only practical applications but also on practical experience of the A.I. systems concerned. It will also emphasize issues associated with the construction of such systems (i.e. problems in building systems for real applications as well as issues of `software' engineering AI systems).

The main subject areas covered will include Evolutionary Computing (GAs and Classifier systems), Neural Networks, Machine Induction, Case Based Reasoning, Expert Systems and Model-Based Reasoning.

The structure of this module is that during the 20 lecture series a number of workshop sessions will run instead of the standard lectures.

Note: students will be expected to undertake a significant amount of self-study throughout this course.

Objectives

• be aware of the implications of a problem domain for the selection of knowledge acquisition methodology, knowledge engineering technique, software development methodology, and system evaluation strategy;
• understand the differences between the main classes of application oriented intelligent system, including representation and reasoning facilitites, and performance issues;
• understand the different techniques and methodologies available for knowledge acquisition, and their relative strengths and weaknesses;
• appreciate the problem of software engineering for intelligent systems;
• have had practical exposure to a range of intelligent systems: including an expert system shell; a CBR toolkit; a neural network simulator and a knowledge acquisition environment.

Overview of AI Systems - 1 Lecture

This lecture will cover the reasons for building Intelligent Systems, the problems associated with building such systems and the benefits companies have obtained from these systems.

Classes of knowledge based system - 1 Lecture

This lecture will introduce the various classes of intelligent system which can be constructed. It will introduce classification and construction tasks and consider their features.

Expert Systems - 2 Lectures, 1 Practical

These lectures will build on the introduction to experts systems provided in other AI models. It will introduce the students to commercial expert system shells and wil provide hands on experience of at least one system. It will condider the issues associated with constructing expert systems and of rule-based representations.

Knowledge Acquisition - 2 Lectures, 1 Practical

These lectures will consider the issue of obtaining the knowledge to be used in an expert system. They will be based around the KADS formalism which will be briefly introduced. This formalism guides the expert system building through the process of task identification and knowledge acquisition.

Evolutionary Computing - 2 Lectures, 2 Practicals

The aim of these lectures will be to introduce the basic algorithms and systems used in evolutionary computing, in particular genetic algorithms and classifier systems. The lectures will introduce the various issues in evolutionary computing (such as representation, evaluation, selection, mutation and crossover) as well as available toolkits. To accompany these lectures practical sessions will be run where students will develop their own genetic algorithm application.

Neural Networks - 2 Lectures, 1 Practical

These lectures will introduce the concept behind Neural Networks and investigate some of the more important and useful neural network architectures. They will also aim to give an appreciation of the application of neural computing in industry and how to proceed when constructing such a system. Students will gain experience of the a neural network simulator.

Case Based Reasoning - 2 Lectures, 1 Practical

These lectures will provide the student with an understanding of the techniques which comprise a case-based reasoning (CBR) system. They should also gain an understanding of their strengths and weaknesses as well as when to apply and when not to apply CBR. The lectures will consider the basic structure of a CBR system and the use of a case base, representation and indexing of cases, case retrieval and adaptation, and finally case repair.

Students are likely to need ready access to the following

C. Price. Knowledge Engineering Toolkits. Ellis Horwood, 1990.

G. Luger and W. Stubblefield. Artificial Intelligence and the Design of Expert Systems. Benjamin/Cummings, 1989.

Lawrence Davis. Handbook of Genetic Algorithms. Van Nostrand Reinhold, 1991.

Janet L. Kolodner. Case-based reasoning. Morgan Kaufmann, 1993.

R. Beale and T. Jackson. Neural computing : an introductio. Institute of Physics, 1990.

Version 4.1

John Hunt Departmental Advisor