Combining Reinforcement Learning and Belief Revision – A Learning System for Active Vision. BMVC, 2008 4.2 Results of Working Group: Model Visualization – Towards a Tight Integration of Machine Learning and Visualization

Computer vision can highly benefit from modern learning methods. In the context of an active vision environment we introduce a machine learning ap-proach which is able to learn strategies of object acquisition. We propose a hybrid learning method, called Sphinx, that combines two approaches origi-nating from seperate disciplines of computer science, namely reinforcement learning on the one hand and belief revision on the other. The former rep-resents knowledge in a numerical way, while the latter is based on symbolic logic and allows reasoning. Sphinx is designed according to human cogni-tion and interacts with its environment by rotating objects depending on past perceptions to acquire those views which are advantageous for recognition. Our method was successfully applied in simulations of object categorization tasks.