This module descriptor provides information for an undergraduate module on Evolutionary Computing and Machine Learning. The 15-credit module is led by Terry Fogarty and includes 14 hours of lectures, 14 hours of tutorials/seminars, 2 hours of supervised assessment, and 96 hours of student-centered learning. The module learning outcomes include specifying suitable algorithms for problems, evaluating evolutionary algorithms, and customizing machine learning techniques for tasks.
1. Napier University Undergraduate Module Descriptor
Module Number CS42007 Credit Value 15
:
Module Title Evolutionary Computing and Machine Learning
Module Leader Terry Fogarty
Department Computing Date of Approval
Indicative Student Workload [in Notionally Efficient Student Hours (NESH)]
Contact Flexible Weighting of Assessment Components
Lectures 14 Supervised 60 %
Tutorials / Seminars 14 Continuous 40 %
Practical Indicative Assessment Catalogue Week
(s)
Supervised assessment 2 Coursework 1 10
Student centred learning 14 96
Other (specify)
TOTAL WORKLOAD 44 96
Timetable Details:
Prerequisite(s) [400 characters, normally module numbers and titles]
Any programming module
Learning Outcomes [maximum 8, contained in 1000 characters]
The student will:
1. Specify suitable search algorithms classes for specified search spaces
2. Critically evaluate the use of evolutionary algorithms compare with traditional search algorithms and other stochastic
methods.
3. Compare and contrast differing algorithm parameters and strategies
4. Specify and evaluate different representation and operators for particular problem domains
5. Critically evaluate the use of hybridisation and domain specific knowledge for particular evolutionary algorithms.
6. Critically evaluate the use of back propagation artificial neural networks for particular problem domains.
7. Be able to specify appropriate evolutionary algorithms or other machine learning techniques for particular problems.
8. Customise machine learning techniques to a particular task.
Description of Module Content [maximum 100 words contained in 600 characters]
Traditional Search Algorithms
Evolutionary Algorithm Classes
Representations and Operators
Algorithm Strategies and Parameters
Use of Domain Specific Knowledge
Hybridisation
Back Propagation Neural Networks
Other Non- Evolutionary Machine Learning Techniques
Case Studies
Notes [maximum 240 characters]
Formal Examination Y/N - If yes, duration in Hrs/Mins : Yes 2 Hours