University of Surrey - Guildford
Registry
  
 

  
 
Registry > Provisional Module Catalogue - UNDER CONSTRUCTION & SUBJECT TO CHANGE
View Module List by A.O.U. and Level  Alphabetical Module Code List  Alphabetical Module Title List  Alphabetical Old Short Name List  View Menu 
2011/2 Provisional Module Catalogue - UNDER CONSTRUCTION & SUBJECT TO CHANGE
 Module Code: COM3013 Module Title: COMPUTATIONAL INTELLIGENCE
Module Provider: Computing Short Name: COM3013
Level: HE3 Module Co-ordinator: JIN Y Prof (Computing)
Number of credits: 15 Number of ECTS credits: 7.5
 
Module Availability
AUTUMN 2010
Assessment Pattern

Assessment Pattern

 

Unit(s) of Assessment

 

Weighting Towards Module Mark( %)

 

Exam:

 

2 hour practical examination

 

50

 

 

Coursework (individual):

 

1 piece of assigned coursework, due in week 7

 

25

 

 

Coursework (individual):

 

1 piece of assigned coursework, due in week 12

 

25

 

 

Qualifying Condition(s) 

 

A weighted aggregate of 40% is required to pass the module.

 

 
Module Overview

Module Overview

 

This module gives an introductory yet up-to-date description of the fundamental technologies of   computational Intelligence, including evolutionary computation, neural computing and their applications. Main streams of evolutionary algorithms and meta-heuristics, including genetic algorithms, evolution strategies, genetic programming, particle swarm optimization, ant colony, and immune algorithms will be taught. Basic neural network models and learning algorithms will be introduced. Interactions between evolution and learning, real-world applications to optimization and robotics, and recent advances will also be discussed.    

 

 
Prerequisites/Co-requisites

Pre-requisite/Co-requisites

 

Basic programming skills in C/C++, Matlab; basics of mathematics

 

 
Module Aims

Module Aims

 

The module aims to demonstrate how computing techniques can be used to understanding natural intelligence, such as evolution, learning and development.  Meanwhile, the module intends to show how knowledge gained from understanding natural intelligence be effectively used for solving engineering problems. Finally, this module should arouse students’ interest in researching into nature-inspired computing techniques for understanding nature and problem solving.  This module also aims to train the students for doing independent research, such as doing literature search, making a research proposal and presenting research results.

 

 

 
Learning Outcomes

Learning Outcomes

 

By the end of the course the students will be able to:

 

·          Understand the major principles of computational intelligence

 

·          Gain hands-on knowledge and experience on designing evolutionary algorithms and neural network based learning algorithms for problem solving

 

·          Perform in-depth research on topics related to computational intelligence. 

 

 

 
Module Content

Module Content

 

Lesson 1: Introduction

 

·          Natural intelligence

 

·          Computational intelligence

 

·          Understanding nature and solving engineering problems

 

·          Professional organizations, major journals and conferences

 

 

Lesson 2: Evolutionary Algorithms

 

·          A generic framework

 

·          Genetic representations

 

·          Genetic variations

 

·          Selection schemes

 

 

Lesson 3:  Swarm Intelligence

 

·          Swarm intelligence in nature

 

·          Particle swarm optimization

 

·          Adaptive PSO

 

 

Lesson 4: Multi-Objective Evolutionary Algorithms

 

·          Dynamic weighted aggregation

 

·          Dominance-based selection

 

·          Elitist non-dominated sorting genetic algorithms

 

·          Performance measures

 

 

Lesson 5: Neural Network Models

 

·          Multi-layer perceptrons

 

·          Radial-basis-function networks

 

·          Other neural network models

 

 

Lesson 6: Learning Algorithms

 

·          Supervised learning

 

·          Unsupervised learning

 

·          Other learning schemes

 

 

Lesson 7: Hybrid Systems I

 

·          Evolutionary optimization of neural networks

 

·          Knowledge extraction from neural networks

 

·          Knowledge incorporation into neural networks

 

 

Lesson 8: Hybrid Systems II

 

·          Memetic algorithms

 

·          Baldwin learning

 

·          Lamarckian learning

 

·          Meta-memetic algorithms

 

 

Lesson 9: Surrogate-Assisted Evolutionary Optimization

 

·          Evolutionary computation for expensive problems

 

·          Basic model management

 

·          Advanced model management

 

·          Evolutionary optimization of aerodynamic structures

 

 

 

Lesson 10: Evolutionary Optimization in Uncertain Environments

 

·          Changing environments

 

·          Search for robust solutions

 

·          Tracking moving optima

 

 

 

Lesson 11: Evolutionary Morphogenetic Robotics

 

·          Evolutionary robotics

 

·          Morphogenetic swarm robotic systems

 

 

 

 
Methods of Teaching/Learning

Methods of Teaching/Learning

 

The delivery pattern will consist of:

 

·          2-hour lectures

 

·          2-hour lab, including coursework, presentation of literature, presentation of mini-projects  

 

per week in weeks 1-11.

 

The labs will require specialized equipment, and the students will have 24-hour access to the facilities.

 

 
Selected Texts/Journals

Selected Texts/Journals

 

There is no single core text that covers the whole course. The following are recommendations for reading.

 

Online Texts:

 

·          Teaching materials will be made available on-line.

 

·          IEEE Computational Intelligence Society: http://www.ieee-cis.org/

 

·          N.J. Nilsson, Machine Learning, available at: http://ai.stanford.edu/people/nilsson/mlbook.html

 

·          T. Hastie, R. Tibshirani, J. Friedman, Elements of Statistical Learning. Springer, 2009 http://www-stat.stanford.edu/~tibs/ElemStatLearn/

 

·          Shark Machine Learning Library: http://shark-project.sourceforge.net/

 

Recommended Texts:

 

·          Andries Engelbrecht, Computational Intelligence: An Introduction by. Wiley & Sons. ISBN 0-470-84870-7

 

 

 
Last Updated
08/09/2010