Machine Learning and Optimisation
Machines that interact with their environment must learn about and optimise their behaviour in that environment. This module aims to provide a grounding in the theoretical and practical aspects of machine learning and optimisation. It also aims to examine some of the philosophical and historical foundations of machine learning, including the limitations of what machines may learn. The core of the module comprises a theoretical and practical introduction to a range of current machine learning and optimisation techniques for supervised learning (principally classification) and unsupervised learning together with standard and evolutionary-based methods for optimising single and multiple objectives (via both population and increment search).
Full module specification
|Module title:||Machine Learning and Optimisation|
|Duration of module:||
Duration (weeks) - term 1: |
0Duration (weeks) - term 2:
11Duration (weeks) - term 3:
This module aims to introduce you to some of the fundamental philosophical ideas surrounding learning machines, before covering a number of different popular techniques and algorithms for machine learning. It also introduces optimisation as both an approach to aid this learning, and as a subject area in its own right (focusing in multi-objective optimisation, that is, where we can measure the quality of a solution against a number of often competing criteria.
ILO: Module-specific skills
- 1. understand some of the main machine learning and advanced optimisation techniques used in artificial intelligence;
- 2. analyse the results of applying a range of machine learning and advanced optimisation techniques, and be able to compare and contrast these results on a range of criteria (and write the necessary software to undertake this);
- 3. apply machine learning and advanced optimisation techniques to significant and real-world problem domains.
ILO: Discipline-specific skills
- 4. comprehend the context in which machine learning sits in relation to computer science and cognitive science;
- 5. demonstrate familiarity with the main trends in machine learning research;
- 6. appreciate the complex and advanced mathematical basis of a range of machine learning and optimisation techniques.
ILO: Personal and key skills
- 7. read and digest research papers from conferences and journals;
- 8. relate theoretical knowledge to practical concerns;
- 9. conduct a research project including robust statistical analysis of experimental results, and contrast the results found with those expected given previously published material.
Learning activities and teaching methods (given in hours of study time)
|Scheduled Learning and Teaching Activities||Guided independent study||Placement / study abroad|
Details of learning activities and teaching methods
|Category||Hours of study time||Description|
|Scheduled learning and teaching activities||22||Lectures|
|Scheduled learning and teaching activities||10||Workshop/tutorials|
|Scheduled learning and teaching activities||30||Project and coursework|
|Guided independent study||88||Wider reading|
|Form of assessment||Size of the assessment (eg length / duration)||ILOs assessed||Feedback method|
Summative assessment (% of credit)
|Coursework||Written exams||Practical exams|
Details of summative assessment
|Form of assessment||% of credit||Size of the assessment (eg length / duration)||ILOs assessed||Feedback method|
|Coursework essay / literature review||30||2500 words||1, 4, 6||Comments directly on essay and on individual feedback sheet|
|Project A||40||20 hours||1, 2, 3, 5, 7||Comments directly on project report and on individual feedback sheet|
|Project B||30||20 hours||1, 2, 3, 5, 7||Comments directly on project report and on individual feedback sheet|
Details of re-assessment (where required by referral or deferral)
|Original form of assessment||Form of re-assessment||ILOs re-assessed||Timescale for re-assessment|
|All above||Coursework (100%)||All||Completed over summer with a deadline in August|
If a module is normally assessed entirely by coursework, all referred/deferred assessments will normally be by assignment.
If a module is normally assessed by examination or examination plus coursework, 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.
- indicative list of topics: historical view of AI (e.g. Turing test, Searle’s Chinese Room arguments);
- introduction to machine learning and optimisation;
- introduction to complexity theory classification methods (e.g. K-NNs, Decision Trees);
- neural computing;
- unsupervised learning methods (e.g. clustering, SOMs);
- mathematical optimisation: nonlinear optimisation, convex optimisation, and online learning for big data;
- other nature-inspired methods as appropriate e.g. ant colony optimisation;
- optimisation methods e.g: evolutionary algorithms for real-world optimisation (e.g. water distribution network optimisation, which may include guest lectures from the Centre for Water Systems);
- simulated annealing gradient descent conjugate gradient multi-objective optimisation combinatorial optimisation.
Indicative learning resources - Basic reading
ELE – http://vle.exeter.ac.uk
- Evolutionary Algorithms for Solving Multi-objective Probelsm,Coello Coello Carlos, Lamont Gary, Veldhuizen David, ,2nd ,Springer,2007,,978-0-387-33254-3
- The Philosophy of Artificial Intelligence,Margaret Boden,,Oxford English Press,1990
- Numerical Recipes: the Art of Scientific Computing,Press, W.H., Flannery, B.P., Teukolsky, S.A. & Vetterling, W.T,3rd edition,Cambridge University Press,2007,518.0285 PRE,13: 9780521880688
Module has an active ELE page?
Last revision date