This project will investigate the structure of everyday common sense knowledge. It aims to find the types of knowledge structures which will facilitate human-like everyday reasoning: recognising concepts in varied instantiations, transferring ideas across varied domains of reasoning, finding connections and similarities, making analogies. Much work in concept representation in Artificial Intelligence focuses on high-level descriptions, often using logics, where the concept has no internal compositional structure. On the other hand subsymbolic approaches have complex nonlinear compositional structures which do not easily generalise to different settings (e.g. different viewpoints in vision, or different contexts/domains in concepts from text) . We aim to come up with an alternative representation which is compositional, but with meaningful parts which have simple relationships among them, so as to allow reasoning and similaritiy-finding in the way that humans find natural and simple. For example if knowledge can be structured with meaningful parts, and flexible representations can be created as the task demands, then one could reason that a frying pan can be used to transfer liquid, or to bash someone; a paper can be used to write on or to start a fire, or to wrap some rice to carry it somewhere; a lecture could be seen to be meandering (this kind of creative use will not be given by a standard ontology). This project will build a more human-like representation of a set of concepts, and a system for conceptual reasoning, which builds on cognitive science works that provide alternative views of concepts. We will avoid toy domains and instead do reasoning with real data in computer vision, robotics and language. Although the project is to be based at Aberdeen, we will also collaborate with experts outside Aberdeen.
The successful candidate should have (or expect to have) a UK Honours Degree (or equivalent) at 2.1 or above in Computer Science or Informatics. Other closely related backgrounds can also be considered, like Engineering or Mathematics with computer algorithms experience (e.g. in Matlab).
Knowledge: Important: programming ability (in any language) Also Desirable: some knowledge of any of: machine learning, basic robotics, computer vision, cognitive science
APPLICATION PROCEDURE: This project is advertised in relation to the research areas in the discipline of Computing Science. Formal applications can be completed online: http://www.abdn.ac.uk/postgraduate/apply. You should apply for PhD in Computing Science, to ensure that your application is passed to the correct College for processing. NOTE CLEARLY THE NAME OF THE SUPERVISOR and EXACT PROJECT TITLE ON THE APPLICATION FORM.
Informal inquiries can be made to Dr F Guerin ([email protected]) with a copy of your curriculum vitae and cover letter. All general enquiries should be directed to the Graduate School Admissions Unit ([email protected]).
There is no funding attached to this project, it is for self-funded students only