Integration of Learning and Reasoning Techniques

Abstract

Since the early days of AI, automated reasoning has been a rather elusive goal. In fact, up till the early nineties, general inference beyond hundred variable problems appeared infeasible. Over the last decade, we have witness a qualitative change in the field: current reasoning engines can handle problems with over a million variables and several millions of constraints. I will discuss what led to such a dramatic scale-up, and how progress in reasoning technology has opened up a range of new applications in AI and computer science in general. I will also discuss initial progress on the use of learning techniques in reasoning engines and the remaining challenges for obtaining a true integration of learning and reasoning.