Research areas

Knowledge representation and machine learning (ML) are two of the most prominent areas of AI, but have largely been developed as independent research directions. Human intelligence, however, often dextrously combines deductive reasoning, incomplete knowledge, search and induction. Moreover, in many mainstream applications, including self-driving cars, it is becoming increasingly important to combine abstract pieces of knowledge (e.g., symbolic, high-level and declarative) with low-level data-intensive pattern recognition and learning.

This area broadly looks at the intersection of machine learning and symbolic systems (logics, programs), in service of the science and technology of artificial intelligence. We are most keen on computational frameworks that are able to explain their decisions, modular, and robust to variations in problem description.