2015/16 | Engineering, Mathematics and Physical Sciences Intranet

MODULE TITLE	Nature-Inspired Computation	CREDIT VALUE	15
MODULE CODE	ECMM409	MODULE CONVENER	Prof Edward Keedwell (Coordinator)

DURATION: TERM	1	2	3
DURATION: WEEKS	11 weeks	0	0

Number of Students Taking Module (anticipated)	2

DESCRIPTION - summary of the module content

Traditional computation finds it either difficult or impossible to perform a wide range of tasks including product design, decision making, logistics and scheduling, pattern recognition and problem solving. However, nature is 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 you if you have an interest in optimisation and data analysis, and have some programming and mathematical experience.

Pre-requisite - ECMM3412 or equivalent

AIMS - intentions of the module

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 which algorithm to select for a given problem,

INTENDED LEARNING OUTCOMES (ILOs) (see assessment section below for how ILOs will be assessed)

On successful completion of this module, you should be able to:

Module Specific Skills and Knowledge:

1 demonstrate deep understanding of the difficulties associated with certain intelligence-related tasks that we would wish to program computers to do;

2 comprehend and implement several diverse nature-inspired algorithms, and appreciate the circumstances and environments in which they are best employed.

Discipline Specific Skills and Knowledge:

3 implement software for addressing either large-scale real-world scheduling and optimisation problems or complex real-world pattern recognition problems;

4 comprehend software for producing lifelike simulations of certain natural behaviours.

Personal and Key Transferable/ Employment Skills and Knowledge:

5 analyse and choose appropriate techniques for given problems from a very diverse toolbox of methods;

6 understand how new ideas in science and engineering can emerge from lateral thinking and ideas from other disciplines;

7 synthesise and succinctly communicate information from publications in the field to individuals unfamiliar with the material;

8 work effectively as part of team to design, implement and demonstrate a system to solve a problem.

SYLLABUS PLAN - summary of the structure and academic content of the module

- 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.

LEARNING AND TEACHING

LEARNING ACTIVITIES AND TEACHING METHODS (given in hours of study time)

Scheduled Learning & Teaching Activities	88.00	Guided Independent Study	62.00	Placement / Study Abroad

DETAILS OF LEARNING ACTIVITIES AND TEACHING METHODS

Category	Hours of study time	Description
Scheduled learning and teaching activities	18	Lectures
Scheduled learning and teaching activities	60	Individual-assessed work
Scheduled learning and teaching activities	10	Supervisory meetings for team project
Guided independent study	62	Private study

ASSESSMENT

FORMATIVE ASSESSMENT - for feedback and development purposes; does not count towards module grade

Form of Assessment	Size of Assessment (e.g. duration/length)	ILOs Assessed	Feedback Method
Not applicable

SUMMATIVE ASSESSMENT (% of credit)

Coursework	70	Written Exams	0	Practical Exams	30

DETAILS OF SUMMATIVE ASSESSMENT

Form of Assessment	% of Credit	Size of Assessment (e.g. duration/length)	ILOs Assessed	Feedback Method
Programming	20	20 hours	2,3,4	Written
Presentation of technical report	10	12-15 slides + handout	1,5,7	Written
Team project	70	3,000 word individual report, team report and program code (shared)	1,5,6,8	Written

DETAILS OF RE-ASSESSMENT (where required by referral or deferral)

Original Form of Assessment	Form of Re-assessment	ILOs Re-assessed	Time Scale for Re-reassessment
All above	Coursework (100%)	All	Completed over the summer with a deadline in August

RE-ASSESSMENT NOTES

Referred and deferred assessment will normally be by coursework. 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.

RESOURCES

INDICATIVE LEARNING RESOURCES - The following list is offered as an indication of the type & level of
information that you are expected to consult. Further guidance will be provided by the Module Convener

ELE – http://vle.exeter.ac.uk

Reading list for this module:

Type	Author	Title	Publisher	Year	ISBN	Search
Reference	Wolfram; S.	Cellular Automata and Complexity	Perseus Publishing	2002	9780201626643	[Library]
Reference	Eberhart, R. Shui, Y. and Kennedy, J.	Swarm Intelligence	Morgan Kaufmann	2001		[Library]
Reference	Corne, D., Bentley, P. (eds.)	Creative Evolutionary Systems	Morgan Kaufmann	2002	1558606734	[Library]
Reference	Bishop, C	Neural Networks for Pattern Recognition	Clarendon Press	1995		[Library]

CREDIT VALUE	15	ECTS VALUE	7.5

PRE-REQUISITE MODULES	ECM3412
CO-REQUISITE MODULES

NQF LEVEL (FHEQ)	7	AVAILABLE AS DISTANCE LEARNING	No
ORIGIN DATE	Friday 09 January 2015	LAST REVISION DATE	Friday 09 January 2015

KEY WORDS SEARCH	Evolutionary computation; neural networks; swarm intelligence; ant colony optimisation; particle swarm optimisation; artificial immune systems.

Computer Science

ECMM409 - Nature-Inspired Computation (2015)