Fall 2014: CIS 419/519 - Introduction to Machine Learning
Fall 2014: CIS 391 - Introduction to Artificial Intelligence
Spring 2014: CIS 110 - Introduction to Computer Science
Fall 2013: CIS 110 - Introduction to Computer Science
Spring 2013: CMSC 380 - Relational Network Analysis
Spring 2013: CMSC 246 - Programming Paradigms
Fall 2012: CMSC 206 - Data Structures
Fall 2012: CMSC 110 - Introduction to Computing
Spring 2012: CMSC 372 - Artificial Intelligence
Spring 2012: CMSC 206 - Data Structures
Past courses taught at Bryn Mawr, Swarthmore, and UMBC
I'm happy to announce the online textbook Artificial Intelligence for Computational Sustainability: A Lab Companion with Doug Fisher, Bistra Dilkina, and Carla Gomes. This is an experiment in crowd-sourced textbook creation, intended to supplement an AI course with assignments related to sustainability. We presented papers on this project at AAAI'12 and Computational Sustainability 2012.
Office: Levine 264
Office Hours (Fall 2014):
Eric Eaton is a faculty member in the Department of Computer and Information Science at the University of Pennsylvania, and a member of the GRASP (General Robotics Automation, Sensing, Perception) lab. Prior to joining Penn, he was a Visiting Assistant Professor in the computer science department at Bryn Mawr College. His primary research interests lie in the fields of machine learning, artificial intelligence, and data mining with applications to robotics, search & rescue, environmental sustainability, and medicine. In particular, his research focuses on developing versatile AI systems that can learn multiple tasks over a lifetime of experience in complex environments, transfer learned knowledge to rapidly acquire new abilities, and collaborate effectively with humans and other agents through interaction. This research is funded by grants from the Office of Naval Research, the National Science Foundation, and Lockheed Martin.
Before moving into academia, Eric spent two years as a senior research scientist at Lockheed Martin Advanced Technology Laboratories working in applied research. At Lockheed Martin ATL, he led a number of machine learning research projects in the Artificial Intelligence Lab with a focus on their application for a variety of DoD organizations. While at Lockheed Martin, he was also part-time faculty in computer science at Swarthmore College.
Eric received his Ph.D. in computer science from the University of Maryland, Baltimore County (UMBC), focusing on artificial intelligence and machine learning. His dissertation developed methods for selective knowledge transfer between learning tasks and was advised by Marie desJardins. At UMBC, he was a member of the Multi-Agent Planning and LEarning (MAPLE) research group and also a part-time instructor.
Further details are provided in his curriculum vitae.
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 consecutive tasks over long time scales,
- Knowledge transfer between learning tasks, and
- Interactive AI methods that combine
system-driven active learning with extensive user-driven
control over learning and reasoning processes.
I am also interested in applications of AI to robotics, medicine, search and rescue, and sustainability.
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.
This research is currently funded by:
- AFOSR Grant #FA8750-14-1-0069, Co-PI (with Matthew Taylor, PI and Paul Ruvolo, Co-PI)
- ONR Grant #N00014-11-1-0139, PI (with Terran Lane and Paul Ruvolo, Co-PIs)
- ONR Contract #N00014-10-C-0192 via Lockheed Martin ATL, PI
In November 2014, I will be co-chairing the AAAI 2014 Fall Symposium on Knowledge, Skill, and Behavior Transfer in Autonomous Robots.
We had a paper accepted to ICML'14: Online Multi-Task Learning for Policy Gradient Methods by Haitham Bou Ammar, Eric Eaton, Paul Ruvolo, and Matthew E. Taylor.
We had a paper accepted to AAAI'14: Online Multi-Task Learning via Sparse Dictionary Optimization by Paul Ruvolo and Eric Eaton.
We had a paper accepted to the AAAI-14 workshop on Machine Learning for Interactive Systems: An Automated Measure of MDP Similarity for Transfer in Reinforcement Learning by Haitham Bou Ammar, Eric Eaton, Matthew E. Taylor, Decebal Constantin Mocanu, Kurt Driessens, Gerhard Weiss and Karl Tuyls.
I am grateful to have received a grant from the Air Force Office of Scientific Research: Lifelong Transfer Learning for Heterogenous Teams of Agents in Sequential Decision Processes with Matthew Taylor (PI) and Paul Ruvolo (Co-PI)
We completed a special issue of AI Magazine on Computational Sustainability, co-edited by Eric Eaton, Carla Gomes, and Brian Williams. It will appear later in 2014.
Haitham Bon Ammar will be joining my research group and the GRASP lab in November 2013. Welcome, Haitham!
Paul Ruvolo will be leaving his postdoc to become an Assistant Professor at Olin College. Congratulations, Paul!
In March 2013, I chaired the AAAI 2013 Spring Symposium on
Lifelong Machine Learning.
Students and Postdocs
I've been fortunate to work with a number of talented
students on these research projects.
Current Research Assistants
- Haitham Bou Ammar (Postdoc)
- Jose Marcio Luna (Postdoc)
- David Isele (PhD student, CIS)
- Mohammad Rostami (PhD student, ESE)
- Chris Clingerman (PhD student, CIS; Primary advisor: Dan Lee)
- Decebal Mocanu (Visiting scholar at Penn; PhD student at TU Eindhoven)
- Fangyu Xiong (BS 2015, Haverford College)
Alumni and Former Students
Ruvolo (Postdoc 2012-2013, Bryn Mawr College): lifelong learning,
(Continued to a faculty position at Olin College as an Assistant Professor)
- Vishnu Purushothaman Sreenivasan (MS, University of Pennsylvania): multi-task reinforcement learning
- Lisa Lee (BS 2014, Princeton University): multi-task reinforcement learning for robotics
- Jacy Li (BS 2014, Bryn Mawr College): lifelong learning
- Rachel Li (BS 2014, Bryn Mawr College): relational community detection using Gaussian processes
- Caitlyn Clabaugh (BS 2013, Bryn Mawr College):
learning to create automatic A vs B music mashups
(Continued to PhD studies at USC)
- Rose Abernathy (BS 2013, Haverford College): social gaming
- Meagan Neal (BS 2013, Bryn Mawr College): active multi-task learning
- Gabriel Ryan (BS 2013, Swarthmore College): lifelong RL with Horde
- Ben Cutilli (BS 2013, Haverford College): vision and UGV control in USARsim
- Leila Zilles (BS 2012, Bryn Mawr College):
active transfer learning for sparse language translation
(Continued to PhD studies at UWashington under an NSF Grad Fellowship)
- David Wilikofsky (BS 2012, Swarthmore College): bootstrapping RL with human demonstration
- Emily Levine (BS 2012, Bryn Mawr College): learning to predict Parkinson's At Risk Syndrome
- Steven Gutstein (Postdoc 2011-2012): lifelong learning, knowledge transfer (Continued to work for JPMorgan)
- Kerstin Baer (BS 2011, Bryn Mawr College):
continual knowledge transfer
(Continued to PhD studies at Stanford under an NSF Grad Fellowship)
- Alexandra Lee (BS 2011, Bryn Mawr College):
visualizing community detection
(Continued to a Masters program at UWashington)
- Rachael Mansbach (BS 2011, Swarthmore College):
interactive community detection
(Continued to PhD studies at UIUC)