Unit information: Introduction to Artificial Intelligence in 2014/15

Unit name	Introduction to Artificial Intelligence
Unit code	EMAT31530
Credit points	20
Level of study	H/6
Teaching block(s)	Teaching Block 2 (weeks 13 - 24)
Unit director	Professor. Cristianini
Open unit status	Not open
Pre-requisites	EMAT20200 Engineering Mathematics 2, EMAT20920 Numerical Methods with Matlab (or equivalent units; knowledge of Matlab and basic statistics)
Co-requisites	None
School/department	School of Engineering Mathematics and Technology
Faculty	Faculty of Engineering

Description including Unit Aims

A general introduction to the ideas and the tasks of Artificial Intelligence, with an emphasis on their relations to other disciplines, their impact on science and industry, and on mathematical foundations. Based on Matlab case studies. Each area will be exemplified by a case study, and the solution of the case study in Matlab will illustrate the strengths and weaknesses, as well as the potential applications, of the relative techniques.

Aims:

The aim is to give a broad overview of the field of Artificial Intelligence (AI), dividing the field in function of its main goals or challenges (rather than in function of the various existing approaches). The course will present the students with all the key areas of the field if AI, using a case study to illustrate each area, and using MATLAB as the main programming language to solve the case study.

The course will also outline the key steps in the history of the field of AI, the main achievements, and the key challenges ahead.

Intended Learning Outcomes

1. Knowledge of standard approaches in artificial intelligence
2. Experience analysing complex data
3. Rigorously comparing the performance of competing methods
4. Modelling the behaviour of autonomous systems
5. Programming in matlab
6. Probabilistic modeling with belief networks
7. Information retrieval
8. Image classification
9. Solving real world problems
10. Report professionally the results of an investigation

Teaching Information

Lectures & computer laboratories

Assessment Information

The above is tested in 2 pieces of coursework (25% each), and one 2-hour written exam (50%)

• The coursework tests the practical knowledge in the lab, including the use of belief networks, and kernel methods, for the analysis of data including images and text (all learning outcomes)

• The exam tests the theoretical and mathematical understanding of the methods used (learning outcomes 1-4)

Reading and References

Artificial Intelligence: Modern Approach, (2nd Edition)

Stuart J. Russell and Peter Norvig