Steps Toward Robust Artificial Intelligence
Thomas G. Dietterich
Distinguished Professor
ACM/AAAI/AAAS Fellow
Oregon State University, USA
Abstract: The growing capabilities of artificial intelligence technologies are encouraging a wide range of new AI-based applications. Many of these involve making decisions in high-risk situations. We need new algorithms and engineering methodologies to create AI systems that are robust to errors in problem formulation, implementation, deployment, and adversarial attack. This requires robustness to both the “known unknowns” (phenomena that we can model with probability distributions) and the “unknown unknowns” (unmodeled phenomena). This talk will discuss these challenges and describe some of the methods for creating robust AI systems that are emerging from basic and applied research groups around the world.
Bio: Dr. Dietterich (AB Oberlin College 1977; MS University of Illinois 1979; PhD Stanford University 1984) is Distinguished Professor and Director of Intelligent Systems Research in the School of Electrical Engineering and Computer Science at Oregon State University, where he joined the faculty in 1985. Dietterich is one of the pioneers of the field of Machine Learning and has authored more than 130 refereed publications and two books. His research is motivated by challenging real world problems with a special focus on ecological science, ecosystem management, and sustainable development. He is best known for his work on ensemble methods in machine learning including the development of error-correcting output coding. Dietterich has also invented important reinforcement learning algorithms including the MAXQ method for hierarchical reinforcement learning.
Dietterich has devoted many years of service to the research community. He is President of the Association for the Advancement of Artificial Intelligence, and he previously served as the founding president of the International Machine Learning Society. Other major roles include Executive Editor of the journal Machine Learning, co-founder of the Journal for Machine Learning Research, and program chair of AAAI 1990 and NIPS 2000. Dietterich is a Fellow of the ACM, AAAI, and AAAS.