This document provides information on the "Intelligent Systems" module, including its code, level, credit points, location, coordinator, content, aims, learning outcomes, teaching methods, and assessment. The module introduces students to intelligent techniques like fuzzy logic, neural networks, and genetic algorithms through both theoretical and practical lessons. Students will learn to design and implement intelligent systems using MATLAB software. Assessment includes coursework assignments and a final written exam.
1. Module Title Intelligent Systems
Module Code COM623M1A
Module Level 3
Credit Points 20
Semester 1
Module Status Option
Location Magee
Prerequisite(s) Mathematics 1
Corequisite(s)
DR Girijesh Prasad , School of Computing and Intelligent
Module Coordinator
Systems; Magee
Teaching Staff
Dr Girijesh Prasad
Responsible
Contact Hours Lectures 36 hours
Tutorials 12 hours
Practicals 12 hours
Assignment prep. 36 hours
Directed Reading 44 hours
Private Study 60 hours
Academic Topic Electronics and Computing
Rationale The module is designed to introduce the student to the research area of
intelligent techniques such as fuzzy logic, neural networks and genetic
algorithms. This module is structured in four parts. The first introduces the
student to the methods of approximate reasoning and fuzzy systems. The
second part concentrates on neural networks and the learning algorithms
required. The third part describes the area of optimization and search routines
using genetic algorithms. The final part describes hybrid approaches involving
combinations of the three techniques.
The emphasis of the module is on the design and implementation of
intelligent technologies. This will involve practical implementations
through a software approach using the Matlab environment.
Aims The aims of the module are to introduce final year students to the research
domain of Intelligent systems and to provide both a theoretical and practical
description of how such systems are designed and implemented.
2. Learning Outcomes
Upon the successful completion of this module a successful student will be able to:
Understand, design and implement an approximate reasoning system using fuzzy
(i)
logic
(ii) Understand, design and implement a learning system using neural networks
Understand, design and implement an optimisation and search system using
(iii)
genetic algorithms
Understand, design and implement a hybrid intelligent system which combines
(iv)
the complementary aspects of each technology
Content
Fuzzy Logic
Notion of approximate reasoning and fuzzy logic, Fuzzy sets, Membership
functions, Operations on fuzzy sets, Extension principle, Fuzzy relations. Steps in
fuzzy reasoning: Fuzzification, Inferencing, Implication and Defuzzification,
1
Linguistic variables and hedges, Theory of approximate reasoning, Fuzzy rule-based,
Fuzzy reasoning mechanisms. Software and hardware implementation of fuzzy
systems, Effectiveness and limitations of fuzzy systems. Applications in computing
and engineering: Fuzzy control, fuzzy clustering etc
Neural Networks
Bio-inspired origins. Biological neurons and artificial neural models,
Classification of neural networks; Network learning rules: Hebbian, Perceptron,
Delta, Widrow-Hoff learning rule, Multilayer feed-forward networks,
2
Backpropagation learning; Self-organising Maps. Recurrent networks: Elman,
Hopfield networks. Hardware and software implementation of NN. Effectiveness
and limitations of neural network systems. Applications of NN in computing and
engineering: Pattern recognition and business prediction.
Genetic Algorithms
Terminology and bio-inspired origins. Features of a GA: Chromosome and
different representation scheme, fitness measure, population size, evaluation,
3 selection, crossover/recombination, mutation, replacement, and convergence.
How do Gas work and comparison with other search techniques. Effectiveness
and limitations of Gas. Applications of GA in computing and engineering:
Parameter optimization.
Hybrid approaches: Soft computing, Computational Intelligence, Artificial Life
Rationale to why techniques can be combined and the advantages and
4
disadvantages. Description of the various hybrid combinations including their
effectiveness and limitations. Practical applications in electronics and computing
Learning and Teaching Methods
3. Six hours per week are used for lectures and tutorials and practical. The
Tutorials will be tutor-led problem-solving sessions, solving assigned problems
in groups and singly, etc. Coursework takes a variety of forms including open
book tests and assigned problems to solve. The module will use a series of cases
studies related to each part of the course to develop understanding of the subject
material. The students will employ the Matlab simulation tool, an industry
standard simulation package provided by Maths Works Inc.
Assessment.
Coursework Assignments 25%
Written Examination 75%
Course work
CA1 A one hour, open book, multiple choice test, in week 7/8 covering all topics of the
first six weeks. Worth 50% of CA. Quick feedback helps to identify students'
weaknesses and act as a guide for future revision. Full discussion of results and solution
sheet given in week 8. This imprints fundamental concepts and provides feedback.
CA2 A case study issued at the end of week 4 to be completed before week 11. Worth
50% of CA. The case studies enable students to investigate the theory presented in the
lectures in a practical sense by performing simulations in Matlab. This tests the student’s
powers of deeper understanding and analysis.
The coursework measures the student's achievement of learning outcomes (i),(ii), and (iii)
for the module.
Examination
A written examination lasting three hours is completed by the student at the end of the
semester. This will consist of compulsory and optional questions.
The examination measures the student's achievement in all of the four learning outcomes
(i),(ii), (iii) and (iv) for the module.
Overall Mapping of learning outcomes on BEng (Hons) Electronics and Computer
Systems
A1 A2 A3 A4 A5 B1 B2 B3 B4 B5 C1 C2 C3 C4 C5 D1 D2 D3 D4 D5
EX √ √ √
CW √ √ √ √ √ √ √ √ √
Overall Mapping of learning outcomes on BSc (Hons) Computer Science
A A A A A C C C C C C D D D D D
B1 B2 B3 B4 B5 B6 D6
1 2 3 4 5 1 2 3 4 5 6 1 2 3 4 5
EX √ √
4. Overall Mapping of learning outcomes on BSc (Hons) Computer Science
CW √ √ √ √ √ √ √ √ √
Overall Mapping of learning outcomes on BSc (Hons) Computing Major
A1 A2 A3 A4 A5 B1 B2 B3 B4 C1 C2 C3 C4 C5 D1 D2 D3 D4 D5 D6
EX √ √
CW √ √ √ √ √ √ √ √ √
Reading List.
Recommended
1. A.P. Engelbrecht, Computational Intelligence: An Introduction, John Wiley &
Sons, Ltd., 2002.
2. JSR Jang et al, Neurofuzzy and soft computing, Prentice Hall, 1997.
3. Hagan, MT, Demuth HB, Beale, MH, Neural Network Design, Campus
publishing service, Colorado University Bookstore at Boulder 36 UCB, Boulder
Colorado, USA, 1996.
4. F.M. Ham, Principles of Neurocomputing for Science & Engineering, McGraw-
Hill International Edition, 2001.
5. J.M. Mendel, Uncertain Rule-based Fuzzy Logic Systems: Introduction and New
Directions, Prentice Hall, 2001.
6. A.A. Hopgood, Intelligent Systems for Engineers and Scientists, CRC Press,
London. 2000.
7. R. Callan, The Essence of Neural Networks, Prentice Hall Europe, 1999.
8. W Pedrycz, Computational Intelligence – an Introduction, CRC Press 1997.
Indicative
1. Haykin, S.:Neural Networks, A Comprehensive Foundation, Macmillan, 1999.
2. Jace M. Zurada: Introduction to Artificial Neural Systems, PWS Publishing
Company, 1995.
3. M.J. Patyra and D.M. Mlynek: Fuzzy logic –Implementation and Application, Wiley
and Tubner, 1996
4. Kosko, Fuzzy Thinking, Harper Collins 1994
5. Cox, E, Fuzzy Systems Handbook, Academic Press 1993
6. Fogel, David B.. - Evolutionary computation : toward a new philosophy of
machine intelligence. - New York : IEEE Press, 1995. - 0780310381.
7. David E. Goldberg: Genetic Algorithms in Search, Optimisation and Machine
Learning, 1989.
5. Summary Description
Having completed this module the student should have an understanding of the research
area of intelligent techniques. The module will address important implementation issues
and describe the benefits of intelligent techniques in practical applications.