Nature-Inspired Computation

Module description

There are a wide range of tasks, including product design, decision making, logistics and scheduling, pattern recognition and problem solving, which traditional computation finds it either difficult or impossible to perform. However, nature has proven to be highly adept at solving problems, making it possible to take inspiration from these methods and to create computing techniques based on natural systems.  This module will provide you with the knowledge to create and apply techniques based on evolution, the intelligence of swarms of insects and flocks of animals, and the way the human brain is thought to process information.  This module is appropriate for any student with an interest in natural systems, optimisation and data analysis who has some programming and mathematical experience.

Prerequisite module: ECM1410 and ECM1414 or equivalent

Full module specification

Module title:Nature-Inspired Computation
Module code:ECM3412
Module level:3
Academic year:2014/5
Module lecturers:
  • Professor Edward Keedwell - Convenor
Module credit:15
ECTS value:

7.5

Pre-requisites:

ECM1410 and ECM1414 or equivalent

Co-requisites:
Duration of module: Duration (weeks) - term 1:

12

Duration (weeks) - term 2:

0

Duration (weeks) - term 3:

0

Module aims

This module aims to provide you with the necessary expertise to create, experiment with and analyse modern nature-inspired algorithms and techniques as applied to problems in industry and industrially motivated research fields such as operations research.

The module also aims to provide you with knowledge of the limitations and advantages of each algorithm and the expertise to determine the appropriate algorithm selection for a given problem.

ILO: Module-specific skills

  • 1. demonstrate a clear understanding of the difficulties associated with certain intelligence-related tasks that we would wish to program computers to do;
  • 2. describe in broad terms, the execution of each nature-inspired algorithm;
  • 3. discuss the circumstances and environments in which each algorithm is best employed;
  • 4. define the different underlying natural mechanisms of each algorithm and explain how this leads to improved computational performance;
  • 5. evaluate a difficult problem and determine the likely best algorithm selection.

ILO: Discipline-specific skills

  • 6. implement software for addressing real-world optimisation problems with nature-inspired methods;
  • 7. create software for addressing certain complex real-world pattern recognition problems.

ILO: Personal and key skills

  • 8. choose appropriate techniques for given problems from a very diverse toolbox of methods;
  • 9. explain how new ideas in science and engineering can emerge from lateral thinking and ideas from other disciplines;
  • 10. digest and communicate succinctly information from publications in the field to individuals unfamiliar with the material.

Learning activities and teaching methods (given in hours of study time)

Scheduled Learning and Teaching ActivitiesGuided independent studyPlacement / study abroad
211290

Details of learning activities and teaching methods

CategoryHours of study timeDescription
Scheduled learning and teaching activities18Lectures
Scheduled learning and teaching activities3Workshops/tutorials
Scheduled learning and teaching activities30Individual assessed work
Guided independent study99Guided independent study

Summative assessment (% of credit)

CourseworkWritten examsPractical exams
702010

Details of summative assessment

Form of assessment% of creditSize of the assessment (eg length / duration)ILOs assessedFeedback method
Written exam – closed book702 hours1, 2, 3, 4, 5, 8, 9Oral, on request
Coursework – programming2020 hours1,5 and 1 of 6, 7Written
Coursework – presentation1012-15 slides1, 3, 9, 10Written

Details of re-assessment (where required by referral or deferral)

Original form of assessmentForm of re-assessmentILOs re-assessedTimescale for re-assessment
All aboveWritten exam (100%)AllAugust Ref/Def

Re-assessment notes

Referred and deferred assessment will normally be by examination. For referrals, only the examination will count, a mark of 40% being awarded if the examination is passed. For deferrals, candidates will be awarded the higher of the deferred examination mark or the deferred examination mark combined with the original coursework mark.
 

Syllabus plan

- classical vs. nature-inspired computation;
- evolutionary algorithms (including genetic programming and multi-objective evolutionary algorithms);
- ant colony optimisation;
- particle swarm optimisation;
- swarm intelligence;
- neural computation (including multi-layer perceptrons and self-organising maps);
- artificial life;
- cellular automata;
- immune system methods.

Indicative learning resources - Basic reading

Swarm Intelligence, Eberhart, R., Shui, Y. and Kennedy, J., Morgan Kaufmann,2001,001.535 KEN

Neural Networks for Pattern Recognition,Bishop, C,,Clarendon Press,1995,001.534 BIS

An Introduction to Genetic Algorithms,Mitchell, M,,MIT Press,1998,001.535 MIT

Ant Colony Optimization,Dorigo, M and Stutzle, T,,Bradford Book,2004,519.7 DOR

Module has an active ELE page?

Yes

Indicative learning resources - Web based and electronic resources

Creative Evolutionary Systems,Corne, D., Bentley, P. (eds.),Morgan Kaufmann,2002,001.642 CRE,1558606734

Genetic Algorithms in Search, Optimization and Machine Learning,Goldberg, D.,Addison Wesley,1989,001.535 GOL

Cellular Automata and Complexity,Wolfram; S.,Perseus Publishing,2002,511.35 WOL,9780201626643

Origin date

19-11-2012

Last revision date

19-11-2012