University of Surrey - Guildford
Registry
  
 

  
 
Registry > Module Catalogue
View Module List by A.O.U. and Level  Alphabetical Module Code List  Alphabetical Module Title List  Alphabetical Old Short Name List  View Menu 
2010/1 Module Catalogue
 Module Code: EEEM005 Module Title: AI AND AI PROGRAMMING
Module Provider: Electronic Engineering Short Name: EEM.AIP
Level: M Module Co-ordinator: WINDEATT T Dr (Elec Eng)
Number of credits: 15 Number of ECTS credits: 7.5
 
Module Availability

Spring
Assessment Pattern

Components of Assessment
Method(s)
Percentage Weighting
Written Closed-book Examination
85%
Programming Assignment and Labs   15%
 

Qualifying Condition(s) 

 

 

Estimated time to complete assignment: 20 hours.

 

 

One lab exercise (Compulsory minimum mark 30%)		  
 

Module Overview

Students learn about the general field of A.I. as well as the more specialist topics of neural networks and Prolog

 

 

 
Prerequisites/Co-requisites

N/A

 

 

 

Module Aims

The aim is to introduce students to some of the basic ideas and concepts which underline the development of artificially intelligent machine systems and to teach them a programming language which is suited to the implementation of such systems, so that they are brought to a level of awareness where they are able to pursue research in artificial intelligence.
Learning Outcomes

On successful completion of the course the students ought to be able to consider the set of methods which would be needed to develop an intelligent system and ought to have an appreciation of their advantages and limitations.  They should be able to use the set of tools which the lecture topics represent to analyse intelligent tasks and should be able to implement Prolog programs to solve some of these tasks.

 

 

 

Module Content

Lecture Component  Artificial Intelligence                                                                               

Lecturer  TW/KW

Hours  15 Lecture hours with 2 problem classes

 

 

 

1          Historical Overview - Definition of artificial intelligence (AI).Application areas. General problem solving versus specific knowledge. Complexity.

 

 

 

2-6       Heuristic Search - Uninformed versus informed search strategies. Formal properties of A*. Minimax game search, alpha-beta pruning.

 

 

 

7-10     Logic and Resolution - Knowledge representation. Propositional and predicate calculus. Inference rules. Clause form. Resolution strategies. Prolog and logic programming.

 

 

 

11-15   Uncertainty Reasoning - Probabilistic reasoning and Bayes theorem. Belief networks. Dempster-Shafer theory. Fuzzy logic.

 

 

 

 

 

 

 

 

 

Lecture Component  Neural Networks  and AI Programming                                                

 

 

 

Lecturer  TW/KW

 

 

 

Hours  15 lecture hours with interspersed Problem Classes

 

 

 

1-2       Theory of logic programs - facts, queries, logical variables, recursion, rules, Horn clauses, structured data.

 

 

 

3-4       Basic Prolog - execution model, declarative and procedural meaning, backtracking, arithmetic, list representation, negation as failure and difficulties, simple examples.

 

 

 

5-7       Prolog Programming and Techniques - input/output, meta-logical and extra-logical predicates, set predicates, cuts, program development and style, correctness and completeness, Applications

 

 

 

8-10     Multi-Layer Perceptrons - Convergence theorem, non-separability, LMS algorithms, steepest   

 

 

 

             descent, back-propagation, generalisation, learning factors.

 

 

 

11        Radial Basis Function Networks - Multivariable interpolation, regularisation,  comparison with 

 

 

 

             MLP, learning strategies.

 

 

 

12-13                                                         Self-Organising Systems - Hebbian learning, competitive learning, SOFM, LVQ

 

 

 

14-15   Recurrent networks - energy functions, Hopfield net, nonlinear dynamical systems, Liapunov stability, attractors.
Methods of Teaching/Learning

Lectures: 30 hours over 10 weeks

 

 

 

Labs: 4 supervised labs teaching basic Prolog skills

 

 

 

Assignment(s): Programming assignment set and marked by TW (issued week 2; to be handed in week 11.  Compulsory minimum mark 30%).
Selected Texts/Journals

http://www.ee.surrey.ac.uk/Personal/T.Windeatt/teaching.html

 

 

 

Winston, P.H., Artificial Intelligence, 3rd ed, (4th ed due Jan 99), Addison-Wesley.  0-201-600862 (£27.50) [B]

 

 

 

Sterling , L. + Shapiro, E., The Art of Prolog., MIT Press. 0262691639 (£24.95) [B]

 

 

 

Bratko, I. , Prolog Programming for Artificial Intelligence. 3rd ed., Addison-Wesley. 0201416069 (£24.95) [C]

 

 

 

Haykin, H. Neural Networks. 2nd Ed. Prentice Hall 0132733501 [B]
Last Updated

29th July 2009