The growing pervasiveness of computerized systems such as intelligent traffic control and energy supply makes our society vulnerable to faults or attacks on such systems.

Rigorous software engineering and verification tools are crucial to counter this threat. In this DIREC Talk, Professor Kim Guldstrand Larsen from Department of Computer Science, Aalborg University discusses how to combine formal verification and AI to obtain safe strategies. Emphasis will be on the challenges of implementing learning algorithms, argue for their convergence and designing data structures for compact and understandable strategy representation.