Computer Science

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 and to examine some of the philosophical and historical foundations of machine learning, including the limitations of what may be learned. 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).

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, and 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 the quality of a solution is measured against a number of often competing criteria.

Module Specific Skills and Knowledge:
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.

Discipline Specific Skills and Knowledge:
4 understand 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 understand the complex and advanced mathematical basis of a range of machine learning and optimisation techniques.

Personal and Key Transferable/ Employment Skills and  Knowledge:
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.

 

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) Support/Relevance Vector Machines 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

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.

ELE – http://vle.exeter.ac.uk

Reading list for this module: