Title: Enhancing AI Capabilities by Rules: Challenges and Opportunities
Speaker: Thomas Eiter
Brief CV: Prof. Dr. Thomas Eiter, Technique University of Vienna,
Professor of Computer Science
Head of the Knowledge Based Systems Group
Head of the Institute of Logic and Computation
Research interests:
knowledge representation and reasoning
computational logic
algorithms and complexity in AI
declarative problem solving
nonmonotonic logic programming and databases
reasoning about actions and change
intelligent agents
Current and past project activities (selection)
International funding::
LogiCS@TUWien (MCSA COFUND grant #101034440, H2020-EU.1.3.4, H2020-EU.1.3)
Humane AI (grant #820437, H2020-EU.1.2.3)
......
National funding::
Integrated Evaluation of Answer Set Programs and Extensions (FWF P27730)......
Memberships::
ACM (Fellow), IEEE CS, Kurt Gödel Society
Association for Logic Programming (President)
Austrian Society for Artificial Intelligence (ÖGAI)
Fellow of the European Association for Artificial Intelligence (EurAI)
Member of the Austrian Academy of Sciences (ÖAW)
Member of Academia Europea (London)
See the homepage http://www.kr.tuwien.ac.at/staff/eiter/ of Thomas Eiter for more details.
Abstract: In the recent years, Artificial Intelligence has seen a tremendous boost in interest, and
it is widely considered key to future information technology. Much of this interest has been fueled by major
advances in
machine learning, which allow for solving a range of problems building on a data-driven, sub-symbolic
approach. For the solutions available, however, important concerns are robustness, safety, explainability
and
trustworthiness in general. Apparently, symbolic approaches to AI that are built on formal (logic-based)
models have much to offer in this regard. We consider Answer Set Programming (ASP), a prominent rule-based
such
approach that has been gaining popularity for declarative problem solving in many AI applications and
beyond. We then consider developments in ASP to facilitate neuro-symbolic AI, aiming to bridge sub-symbolic
and
symbol-based AI, in order to enhance the capabilities of modern AI systems. We discuss opportun! ities for
ASP, such as reasoning, model-building, and explainability, as well as challenges, e.g. dealing with
uncertainty
and seamless integration, which provide directions for future research.