Example PhD

Learning rules for cellular automata

Supervisor: Professor P.L. Rosin

Keywords: Image Processing, Computer Vision.

Over the last fifty years cellular automata have become increasingly popular, but their application to image processing has been limited by the need to manually generate rule sets. The aim of this project is to investigate general methods for automatically learning good rule sets from training data, which can then be applied to a variety of image processing tasks. The challenge is to perform rule selection efficiently and effectively, whilst avoiding the potential combinatorial explosion that arises when the cell neighbourhood size or the number of cell states.

Key Skills/Background: Strong computing and mathematical skills required

Contact: Professor P.L. Rosin to discuss this research topic.