G5BAIM - Artificial Intelligence Methods

This course is run at the The University of Nottingham within the School of Computer Science & IT. The course is run by Graham Kendall (EMAIL : gxk@cs.nott.ac.uk)

Course Intoduction

Introduction

Welome to the Artificial Intelligence Methods course. This first page introduces you to the course, lets you know what to expect and how to get the most from the course.

The course has been designed so that you have additional course material, other than lectures, in order to help you learn and understand the material. This includes videos, previous exam papers with suggested answers, a bulletin board and a set of self-assessment quizzes that allows you to judge how you are progressing. There will not be the usual "two lectures a week", but rather "key note" lectures to point you in the right direction. Having said that, I plan to do between 10 and fifteen lectures so you don't feel as if I am abandoning you. The provisional lecture schedule can be seen below.

The main web site for this course will be available from my home page.

If you are only interested in the web material then you don't have to register to use WebCT but, if you want to take advantage of the bulletin board and the on-line self-assessment then you need to register to use WebCT. To do this see the frequently asked questions.

Assessment Method

This course is examined by a two hour examination, which accounts for 75% of the marks. Please note that the rubric for the exam will read something like this

"Marks will be awarded for the first FOUR questions in the answer book. Clearly cross through any questions that you do NOT wish to be considered and ensure you state on the front of the answer book the FOUR questions you have attempted."

That is to say, if you answer five or six questions I will only mark four. Unlike some other exams, you cannot answer as many questions as you like and be given marks for the nest four questions.

The remainder of the marks (25%) are given for a piece of couresework.

Additional Reading Material

As part of this course, I have compiled a number of academic papers which you are expected to read. They are listed here for your convinience.

1. Phenotypes and Genotypes (Fogel D. Phenotypes, Genotypes, and Operators in Evolutionary Computation, Proceedings of the 1995 IEEE International Conference on Evolutionary Computation, Perth, Australia, IEEE Press, pp. 193-198)
   
   
2. An Introduction to Genetic Programming (Hirsh H. Geneticprogramming, IEEE Intelligent Systems, 2000, 15(3), pp 74-84)
   
   
3. An Introduction to Genetic Algorithms (Reeves C. Genetic Algorithms for the Operations Researcher, INFORMS Journal on Computing, , 1997, 9(3), pp 231-250)
   
   
4. An Introduction to Ant Algorithms
   • Paper 1 (Dorigo M. and Colorni A. The Ant System: Optimization by a colony of cooperating agents, IEEE Transactions on Sytems, Man, and Cybernetics-Part B, 26(1), 1996, pp 1-13)
     
     
   • Paper 2 (Dorigo M. and Gambardella L M. Ant colonies for the traveling salesman problem, Technical report (Ref:TR/IRIDIA/1996-3), 1996, Universite Libre de Bruxelles, Belgium)
     
     
5. An Introduction to Tabu Search (Hertz A., Taillard E., de Werra D. A Tutorial on Tabu Search. Proc. of Giornate di Lavoro AIRO'95 (Enterprise Systems: Management of Technological
   and Organizational Changes),1995, pp13-24)
   
   
6. An Evolutionary Strategy/Neural Network Case Study
   • Paper 1 (Chellapilla K, Fogel D. Anaconda Defeats Hoyle 6-0: A Case Study Competing an Evolved Checkers Program against Commercially Available Software, Congress on Evolutionary Computation 2000 (CEC'02), pp 857-863)
     
     
   • Paper 2 (text, figures1, figures2) (Chellapilla K. and Fogel D. Evolving Neural Networks to Play Checkers without
     Expert Knowledge,IEEE Trans. Neural Networks, 1999, Vol. 10:6, pp. 1382-1391)
     
     
   • Paper 3 (text, figures, tables) (Chellapilla K. and Fogel D. Evolution, Neural Networks, Games, and Intelligence,
     Proc. IEEE, 1999, Vol. 87:9, Sept., pp. 1471-1496)

Lecture Schedule

 Last Updated : 26/01/2002