Thomas G. Dietterich: Research Bio
How can computers be programmed so that they can learn from their
experience and become more effective over time? How can
high-performance software systems be constructed from data? How can
the vast quantities of scientific and business data be analyzed to
find patterns and suggest hypotheses? These are the questions studied
by Thomas Dietterich and his research group. Among the theoretical
and practical results of this work have been (a) error-correcting
output coding (a method for supervised learning over many categories),
(b) bias/variance analysis of classification problems, (c) methods for
solving multiple-instance learning problems (with applications to
pharmaceutical development), (d) a methodology for applying
reinforcement learning to solve industrial combinatorial optimization
problems, and (e) the MAXQ architecture for hierarchical reinforcement
learning. Dr. Dietterich's current research projects include (a)
anomaly detection methods in computer vision that can detect images
that lie outside the training data (including images that contain
objects belonging to novel classes), (b) statistical methods for
providing prospective performance guarantees for classification and
reinforcement learning, (c) statistical methods for detecting failed
sensors in environmental sensor networks. A continuing theme of
Dr. Dietterich's research is to develop methods for constructing AI
systems that know their own limitations and behave robustly in the
face of unknown unknowns.
Dr. Dietterich (AB Oberlin College 1977; MS University of Illinois
1979; PhD Stanford University 1984) is Distinguished Professor
(Emeritus) and Director of Intelligent Systems in the School of
Electrical Engineering and Computer Science at Oregon State
University, where he joined the faculty in 1985. In 1987, he was
named a Presidential Young Investigator for the NSF. In 1990, he
published, with Dr. Jude Shavlik, the book entitled Readings in
Machine Learning, and he also served as the Technical Program
Co-Chair of the National Conference on Artificial Intelligence
(AAAI-90). From 1992-1998 he held the position of Executive Editor of
the journal Machine Learning. The Association for the
Advancement of Artificial Intelligence named him a Fellow in 1994, and
the Association for Computing Machinery did the same in 2003. In
2000, he co-founded a free electronic journal: The Journal of
Machine Learning Research. He was Technical Program Chair of the
Neural Information Processing Systems (NIPS) conference in 2000 and
General Chair in 2001. He served as the founding president of the
International Machine Learning Society and as the President of the
Association for the Advancement of Artificial Intelligence.
Since 2007, Dr. Dietterich has served as arXiv moderator for Machine
Learning (category CS.LG). He is a member of the Steering Committee of
the DARPA-sponsored ISAT Study Group, and he serves on the Advisory
Boards of the International Machine Learning Society and the NIPS
Foundation.
Shorter Bio
Dr. Dietterich (AB Oberlin College 1977; MS University of Illinois
1979; PhD Stanford University 1984) is Distinguished Professor
Emeritus in the School of Electrical Engineering and Computer Science
at Oregon State University. Dietterich is one of the pioneers of the
field of Machine Learning and has authored more than 225 refereed
publications and two books. His current research topics include robust
artificial intelligence, robust human-AI systems, and applications in
sustainability.
Dietterich has devoted many years of service to the research
community. He is a former President of the Association for the
Advancement of Artificial Intelligence, and 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. He currently serves as one of the moderators for the
cs.LG category on arXiv.