AI systems that learn and reason

Abstract

Symbolic and statistical AI techniques have complementary strengths and weaknesses, prompting many research to investigate combinations of the two: using symbolic knowledge to improve machine learning, or vice versa using machine learning to improve symbolically represented knowledge.
We present a survey of different approaches for combining these techniques, and we propose a unified notation to describe the wide variety of different architectures. This work is in collaboration with Annette ten Teije.

About the speaker

Frank van Harmelen is full professor at the Vrije Universiteit Amsterdam, where he leads the Learning and Reasoning group. He has been a leading contributor to widely used semantic web techniques, including the web ontology language OWL and one of the first scalable triple stores (Sesame, which earned him the 10-year impact award of the International Semantic Web Conference). He is one of the editors of the Handbook of Knowledge Representation, the standard reference in his field, and he is member of the Royal Netherlands Academy of Sciences and of Academia Europaea.