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.

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.    

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

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.

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. 

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

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.

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