Thomas G. Dietterich

E-mail: tgd@cs.orst.edu Twitter: @tdietterich Phone: +1-541-737-5559 Office: KEC 2067
PGP Public Key
(Last updated June 12, 2020)

Page Contents: Research Prospective Students Publications Talks CV Software Students and Staff Course Materials Bio Sketch

Current Research

"If you invent a breakthrough in artificial intelligence, so machines can learn," Mr. Gates responded, "that is worth 10 Microsofts." (Quoted in NY Times, Monday March 3, 2004)

The focus of my research is artificial intelligence and machine learning. How can we make computer systems that adapt and learn from their experience? How can we combine machine learning with other advances in AI to build Integrated Intelligent Systems? How can we make those integrated AI systems robust to errors, both known and unknown? How can we combine human knowledge with massive data sets to expand scientific knowledge and build more useful computer applications? My laboratory combines research on machine learning and AI fundamentals with applications to problems in science and engineering.

• Scientific Projects
  • Robust Artificial Intelligence. AI methods are widely deployed in many parts of the economy including search engines, speech-enabled systems, computer vision, and natural language translation. Automated reasoning tools developed in AI have been integrated with traditional algorithms from operations research to create very powerful optimization programs such as Gurobi and CPLEX. Of particular concern are AI applications that involve life-and-death decision making such as self-driving cars, AI control of the power grid, and autonomous weapons systems. Before we deploy AI in such applications, we need to be confident that it will behave correctly.

    With my colleagues and students, I'm pursuing research in safe artificial intelligence including open category supervised learning, safe reinforcement learning, and explainable artificial intelligence. I've reviewed the research challenges in this area in my AAAI Presidential Address, Steps Toward Robust Artificial Intelligence. Slides, Video, Paper.

  • Ecosystem Informatics and Computational Sustainability: Oregon State University is a leader in combining computer science and the ecological sciences to build the new discipline of Ecosystem Informatics. Ecosystem Informatics studies methods for collecting, analyzing, and visualizing data on the structure and function of ecosystems. It is part of the larger field of Computational Sustainability.

    Oregon State is also part of the Institute for Computational Sustainability led by Cornell University. This effort seeks to develop novel computational methods to address problems in ecosystem science and sustainable management of the biosphere.

    My group is involved in many Ecosystem Informatics and Computational Sustainability activities:

    • Approximate Optimization for Bio-Economic Models. Many sustainability applications require solving large spatio-temporal optimization problems under uncertainty. We are collaborating with natural resource economists on methods for approximate solution of spatio-temporal optimization problems involving land management for wildfire control and counter-measures for controlling invasive species.

    • Project TAHMO: Deployment, Cleaning, and Analysis of Sensor Network Data. We are part of the Project TAHMO that seeks to construct and deploy a network of 20,000 hydro-meteorological stations in Africa. We are developing algorithms for sensor placement, data cleaning, recovery from damaged sensors, and analysis of the resulting data. We are building on our previous work with Ethan Dereszynski on dynamic Bayesian network models for sensor data cleaning.

    • NIPS 2012 Posner Lecture: Challenges for Machine Learning in Computational Sustainability.

    • ICML 2011 Tutorial on Machine Learning in Ecology and Ecosystem Management

  • Intelligent Desktop Assistants. We have been involved in two large efforts to develop intelligent assistants for the computer desktop.

    • TaskTracer. When you come into work in the morning, you don't want to say to your computer "I want to run Word", but rather, "I want to work on my CS534 homework". In other words, you would like a user interface that was organized around your projects and activities rather than around application programs, files, folders, etc. You would also like all of your information in one place rather than scattered across the local file system, network file systems, dropbox, web sites, email folders, calendar, contacts, etc. TaskTracer extends the Windows UI to provide exactly this functionality. This research is supported by a gift from Keysight, Inc. with previous support from Google, Intel, and the DARPA CALO project.

  • Fundamental Machine Learning and Artificial Intelligence Research

    • Anomaly Detection. An important capability for AI systems is to be able to detect when an input situation is unusual. For example, anomaly detection can allow machine learning systems to detect when an input case is very different from the training data and hence could lead to extrapolation and poor performance. Anomaly detection methods are also important for detecting novel failures in sensor networks and novel attacks on computer systems. We are developing a range of algorithms for anomaly detection under grants from the National Science Foundation, the Future of Life Institute, and a gift from Huawei, Inc.

      We have also developed a new benchmarking methodology for comparing anomaly detection methods. Benchmark data sets and scripts are available for download.

    • Sample-Efficient Algorithms for Solving Markov Decision Processes. We are developing algorithms for solving MDPs in which the state consists of a landscape of patches, and each patch has its own state. This means that the state space is enormous. At each time step, an action must be specified for each patch, so the action space is also enormous. In these problems, phenomena (such as fires, infections, species spread) propagate spatially, so we cannot treat the patches as independent. Our algorithms seek exact (or bounded approximate) solutions for small problem instances, and satisfactory solutions for real-sized problem instances. Our algorithms optimize both expected (discounted) cumulative reward and also risk-sensitive reward measures. The transition probabilities for these models are specified in the form of an expensive simulator which can be invoked with a given state and action to obtain a sample of the resulting state and the reward. An important goal is to minimize the number of calls to the simulator.

    • Exogenous State MDPs We are also studying MDPs where some of the state variables cannot be controlled by the policy. These exogenous state variables can confuse reinforcement learning algorithms, so we seek methods for identifying and ignoring these variables.

  • Reviews, tutorials, and books. I have written several review articles and tutorials on machine learning.

  ---

  Information for Prospective Students

  If you are seeking a research career in machine learning, data mining, artificial intelligence and related areas, and you have a strong background in mathematics and programming, please read my Information for Prospective Students page.

  If you are interested in robotics, I encourage you to visit the Robotics Team Pages to learn more about our excellent robotics program.

  ---

  Publications, Curriculum Vita, Software, and Data

  • Publications
  • Talks
  • Curriculum Vita
  • Downloadable Collection of Error Correcting Codes for use with the error-correcting output coding technique.
  • Release 1.0 of MAXQ Hierarchical Reinforcement Learning code.
  • RSW (Recurrent Sliding Window) Package for WEKA for sequential supervised learning.
  • Implementation of the PCBR region detector developed as part of the BugID project.
  • Implementation of TreeCRF system and supporting materials from our JMLR paper. Java implementation by Brad Block.
  • STONEFLY9 Image Database.
  • EPT29 Image Database.
  • Starcraft Scouting dataset (for UAI 2012 paper)

  ---

  Professional Service, Journals, and Book Series

  • I am one of the moderators for the machine learning (CS.LG) part of CoRR, which is the computer science sub-part of arXiv.
  • I am a member of the Editorial Board for the Journal of Machine Learning Research, which is an electronic (and hardcopy) journal covering all areas of machine learning.
  • I am a former President of the Association for the Advancement of Artificial Intelligence.
  • I am past President of the International Machine Learning Society.

  ---

  Entrepreneurial Activities

  • I am a co-founder of Strands (formerly MyStrands; formerly MusicStrands), a recommendation company.
  • I am a co-founder of Smart Desktop. Smart Desktop is now part of Decho, Inc., which is a "cloud computing" effort of EMC. Decho was a spinout of the TaskTracer project.
  • I am a co-founder and Chief Scientist of BigML. The goal of this startup is to develop large scale cloud-based machine learning services.

  ---

  Current Students and Staff

  • Andrew Emmott, Graduate Student.
  • Risheek Garrepalli, Graduate Student (Jointly supervised with Alan Fern).
  • Jed Irvine, Senior Faculty Research Assistant (Software Engineer).
  • Si Liu, Graduate Student (jointly advised with Debashis Mondal, Statistics).
  • Michael Slater, Graduate Student.
  • Pat Sullivan, Assistant and Grants Coordinator.
  • Tadesse Zemicheal, Graduate Student.

  Former Students and Staff

  • Majid Alkaee Taleghan. Machine Learning Scientist at Context Relevant.
  • Hussein Almuallim, Oil and Energy Professional, Calgary, Canada.
  • Eric Altendorf, Google.
  • Adam Ashenfelter, BigML, Inc., Corvallis, Oregon.
  • Ghulum Bakiri, President at MicroCenter, Bahrain.
  • Christian Baumberger. Software Engineer at Zuehlke Group
  • Xinlong Bao. Google Pittsburgh.
  • Brian Breck.
  • Waranun Bunjongsat.
  • Giuseppe Cerbone. Independent Information Services Professional, Milan, Italy.
  • Martha Chamberlin.
  • Hei Chan. Assistant Professor / Project Researcher at the Transdisciplinary Research Integration Center, UCLA.
  • Richard Charon.
  • Eric Chown, Full Professor, Bowdoin College.
  • Selina Chu, JPL, Pasadena, CA.
  • Dan Corpron
  • Mark Crowley, Assistant Professor, Department of Electrical and Computer Engineering, University of Waterloo.
  • Diane Damon, Damon Consulting, Portland, OR.
  • Ethan Dereszynski, Research Scientist, WebTrends, Portland, OR.
  • Phuoc Do, Vida Lab.
  • Nicholas Flann Associate Professor, Utah State University
  • Greg Foltz.
  • Dan Forrest.
  • Tony Fountain, Director of the Cyberinfrastructure Lab for Environmental Observing Systems (CLEOS), UC San Diego.
  • Ashit Gandhi, Founder and Vice-President, Prism Gem, LLC - The Art of Diamond Coloring.
  • Colin Gerety, Fort Collins, CO.
  • Brandon Harvey, Symantec and Linn-Benton Community College.
  • Arwen Griffioen.
  • Guohua Hao, Senior Data Scientist at iHeartRadio.
  • Hermann Hild, President, SMI Cognitive Software GmbH .
  • Jesse Hostetler
  • Rebecca Hutchinson, Assistant Professor of Computer Science and Fishers and Wildlife.
  • Saket Joshi, Member of Technical Staff at Cycorp.
  • Varad Joshi, Director of Engineering at Elemental Technologies.
  • Caroline Koff, Hewlett-Packard Corporation, Fort Collins, CO.
  • Victoria Keiser, Research Programmer, CMU. Masters Thesis (PDF).
  • Michael Kelm, Research Scientist, Siemens Healthcare.
  • Eun Bae Kong, Professor, Computer Science, Chungnam National University, South Korea
  • Bill Langford, Research Associate at RMIT, Melbourne, Australia.
  • Junyuan Lin, VMWare, Seattle.
  • Liping Liu, Postdoc with David Blei, Columbia University.
  • Dragos Margineantu, The Boeing Company.
  • Gonzalo Martinez, Assistant Professor, Autonomous University of Madrid.
  • Sean McGregor. XPRIZE.
  • Prafulla Mishra, Software Development Manager at eBay.
  • Avis Ng.
  • Soumya Ray, Assistant Professor, Case-Western Reserve University.
  • Angelo Restificar, Principal Machine Learning Engineer, EBay, Seattle.
  • Ritchey Ruff, Senior SDET, Microsoft.
  • Dan Sheldon, Assistant Professor, University of Massachusetts, Amherst.
  • Jianqiang Shen. Research Scientist, PARC. Doctoral dissertation.
  • Rongkun Shen. Post-doc, Oregon Health and Science University, Portland.
  • Michael Shindler, Lecturer at the University of Southern California
  • Shriprakash Sinha. Ph.D. student TU Delft.
  • Shahed Sorower, Scientist at Philips Research North America (Cambridge, MA.)
  • Simone Stumpf. Senior Lecturer, City University London.
  • Amelia Snyder, Intern at World Resources Institute
  • Tao Sun, Graduate Student at UMass Amherst.
  • Dan Vega, Senior Software Engineer at Valley Inception, LLC.
  • Mark Vulfson. Microsoft Corporation.
  • Kiri Wagstaff, Principle Researcher at JPL.
  • Xin Wang, Senior Scientist at Inome (Intelius).
  • Dietrich Wettschereck. Consultant, Cologne, Germany.
  • Pengcheng Wu.
  • Michael Wynkoop, Qualcomm.
  • Qing Yao, College of Informatics and Electronics. Zhejiang Sci-Tech University. Hangzhou, China.
  • Wei Zhang, The Boeing Company.
  • Wei Zhang. Senior Software Engineer, Google. Doctoral Dissertation (PDF).
  • Valentina Zubek, Principal Statistician, Boehringer Ingelheim.

  ---

  Previous Courses and Courseware

  • Tsinghua Short Course on Trustable Machine Learning, Fall 2018
  • CS519/GEO599: Principles of Ecosystem Informatics, 2004-2005.
  • CS 534, Spring 2005, Machine Learning.
  • CS430, Fall 2003, Introduction to Artificial Intelligence
  • CS539, Fall 2003, Seminar: Probabilistic Relational Models
  • CS 533, Applied Artificial Intelligence for Engineeers.
  • CS 539, Winter 2000, Selected Topics in Artificial Intelligence: Probabilistic Agents
  • CS 430/530, Fall 1999, Artificial Intelligence Programming Techniques.
  • CS 519, Fall 1996. Research Methods in Computer Science.
  • CS 450/550, Winter 1996, Introduction to Computer Graphics.

  ---

  Machine Learning Resources

  • ML-News is an email list operated by the IMLS for conference annoouncements, job positions (including graduate student and postdoc offers), and other items of relevance to the machine learning community. To join, you must have a google account. Log in to google and then go to the ML-News main page and click on "Apply to join group". Please include your affiliation in your join request.
  • How to be a Graduate Student. A great web page with pointers to lots of good resources for graduate students.
  • Standard Proofreading Symbols that I use when marking corrections on papers.
  • Computing Research Repository (part of arXiv). I am the moderator for machine learning.
  • Research Index at Penn State. An invaluable resource for finding online articles, citations, etc.
  • Journal of Machine Learning Research (JMLR). (Free electronic and hardcopy journal.)
  • Machine Learning. (Expensive hardcopy journal.)
  • Journal of Artificial Intelligence Research (JAIR). (Free electronic and hardcopy journal.)
  • The Machine Learning Database Repository at UC Irvine.
  • StatLib containing data, algorithms, and other information relevant to statistics.
  • Knowledge Discovery Mine containing information about knowledge discovery in databases.
  • NIPS Online Proceedings.
  • CMU Reinforcement learning group.
  • Bibliographies on Artificial Intelligence
  • The DBLP Computer Science Bibliography.
  • Numerical Recipes Homepage.

  ---

  My Family's Musical Activities

  • yOya on MySpace and yOya home page. My son Noah writes songs and plays keyboards for this band.

  • Jubilate: The Women's Choir of Corvallis. My wife Carol sings in this choir.

  Tom Dietterich, tgd@cs.orst.edu