Teaching

Swarthmore College
Fall 2009:    CPSC 063 - Artificial Intelligence

University of Maryland Baltimore County
Fall 2007:    CMSC 471 - Artificial Intelligence
Fall 2006:    CMSC 121 - Introduction to Unix (Sections 0101 & 0102)
Fall 2005:    CMSC 121 - Introduction to Unix (Section 0102)
Spring 2005:    CMSC 203 - Discrete Structures

About Eric

Eric Eaton is a Senior Research Scientist in the Artificial Intelligence Lab at LM ATL and a part-time Visiting Assistant Professor in the Computer Science Department at Swarthmore College. He received his Ph.D. in computer science from UMBC, focusing on artificial intelligence and machine learning. At UMBC, he was a member of the Multi-Agent Planning and LEarning (MAPLE) research group, advised by Marie desJardins. His dissertation developed methods for selective knowledge transfer between learning tasks.

Eric also earned M.S. and B.S. summa cum laude degrees in computer science at UMBC, with his Masters thesis focusing on constrained clustering. Outside of academia, Eric was active in the local theatre community for many years as a director, stage combat choreographer, and actor. For details on his theatrical endeavors and funny pictures, please see his (now outdated) theatre website.

Research

My primary research interests are in the areas of artificial intelligence and machine learning, with a focus on the following topics:

  • Lifelong learning of multiple sequential tasks over long time scales,
  • Knowledge transfer between learning tasks,
  • Representation discovery, which learns features of the environment to best support learning, and
  • Interactive AI methods that provide the user with extensive control over reasoning and learning processes.

My other interests include: pattern discovery in temporal data, preference learning, and applications of AI to medicine, search and rescue, and space exploration.

Details of my research on these topics can be found on my research and publications pages. This research has also produced a number of software packages, which I make freely available for academic and not-for-profit use.