Intelligent Systems MSc/PG Dip/PG Cert

• Computational Intelligence Research Methods details quantitative and qualitative approaches including laboratory evaluation, surveys, case studies and action research.
• Fuzzy Logic considers the various fuzzy paradigms that have become established as computational tools.
• Natural Language Processing focuses on Natural Language Processing (NLP) using Python. It uses NLTK and Pytorch. NLTK is a leading platform for NLP which provides a number of text processing libraries for classification, tokenization, stemming, tagging, parsing, and semantic reasoning, wrappers for industrial-strength NLP libraries. Pytorch provides access to deep learning function which can be applied to NLP problems.
• Mobile Robots discusses the hardware and software architectures used to build mobile robot systems.

• Computational Intelligence Optimisation (CIO) is a subject that integrates artificial intelligence into algorithms for solving optimisation problems that could not be solved by exact methods. Thus, CIO is the subject that defines and designs metaheuristics, i.e. general purpose algorithms. This makes CIO the subject that tackles optimisation problems in engineering, economics, and applied science
• Artificial Neural Networks and Deep Learning appraises neural network computing from an engineering approach and the use of networks for cognitive modelling.
• Applied Computational Intelligence considers knowledge-based systems; the historical, philosophical and future implications of AI; then focuses on current research and applications in the area
• Intelligent Mobile Robots covers sensing, representing, modelling of the environment, adaptive behaviour and social behaviour of robots. OR
• Data Mining, Techniques and Applications examines the tools and techniques needed to mine the large quantities of data generated in today’s information age. It provides practical experience as well as consideration of research and application areas

Summer:

• Individual Project provides the opportunity to demonstrate skills acquired from the course in a problem solving capacity. This typically involves the analysis, design and implementation of a computer system.

The course consists of an induction unit, eight modules and an individual project. The summer period is devoted to work on the project for full-time students. If you choose to study via distance learning, you would normally take either one module per semester for four years or two modules per semester for four years plus a further year for the project.

Teaching is normally delivered through lectures, seminars, tutorials, workshops, discussions and e-learning packages. Assessment is via coursework only and will usually involve a combination of individual and group work, presentations, essays, reports and projects.

Distance learning material is delivered primarily through our virtual learning environment. Books, DVDs and other learning materials will be sent to you. We aim to replicate the on-site experience as fully as possible by using electronic discussion groups, encouraging contact with tutors through a variety of mediums.

Contact and learning hours

On-site students will have the lessons delivered by the module tutors in slots of three hours. In the full-time route, you can expect to have around 12 hours of timetabled taught sessions each week, with approximately 28 additional hours of independent study. There are also three non-teaching weeks when fulltime students can expect to spend around 40 hours on independent study each week.