General description
This module concentrates on the technology and methodology of Artificial Intelligence practice, in particular, programming languages and software systems. The aim is to build on the concepts introduced in CS26210 and show how knowledge-based systems can be implemented, developed and evaluated.

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

Learning outcomes
On successful completion of this module students should:

• understand the differences between the main classes of application oriented intelligent system, including representation and reasoning facilitites, and performance issues;

• understand the issues involved in constructing effective diagnostic systems;

• appreciate the problem of software engineering for intelligent systems;

• have familiarity with current machine learning and data mining techniques and tools.

Syllabus
1. Effective Diagnostic Expert Systems - 3 Lectures
Building on CS36210, these lectures will introduce how to build effective diagnostic systems for man made systems. It will therefore look at diagnostic trees, diagnostic test benches and issues associated with diagnostic systems. From these lectures the student should gain an understanding of the features of commercial expert systems tools and their strengths and limitations.

2. Case based reasoning - 2 Lectures
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 for diagnostic applications 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.

3. Model-based Reasoning - 3 Lectures
In these lectures "Functional" model based reasoning will be introduced. How a functional model-based system can be constructed and the problems and issues associated with such a task will be considered. In addition a functional model-based system constructed for Engineers will be considered in detail. This case study will highlight the trade offs which had to be made between ease of use and flexibility, power, etc.

4. MBR for Failure Mode Effect Analysis - 2 Lectures
These lectures will look at how MBR can be used as the basis of a design analysis system which can be used to provide information necessary for the construction of diagnostic systems.

5. Neural Networks - 3 Lectures
These lectures will introduce the concepts 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.

6. Machine Induction - 3 Lectures
There are a large number of applications which exploit the approach to machine learning known as induction. In these lectures we will consider the application pf these methods.

7. Inductive Logic Programming - 2 Lectures
Inductive Logic Programming (ILP) is a new and exciting development in AI systems which has a wide range of applications. These lectures will introduce ILP and the issues associated with applying ILP to real world problems.

8. Data Mining - 2 Lectures, 1 Practical
Data mining has become one of the fastest growing application areas in AI. It combines various AI techniques such as neural networks and machine induction with statistical analysis and database techniques. A commercial Data Mining tool "Clementine" will be considered during these lectures.