Matthew D. Schmill
PO Box 12
Hyattsville, MD 20781
Phone: (413)244-3777
Email: matt@schmill
Web: matt.schmill
Education
5/1997 – 5/2004University of Massachusetts, Amherst
Ph.D., Computer Science
Title: Learning the Structure of Activity for a Mobile Robot
Advisor: Paul R. Cohen
Committee: Neil Berthier, Paul R. Cohen, Rod Grupen,
Victor Lesser
9/1995 – 5/1997University of Massachusetts, Amherst
M.S., Computer Science
Advisor: Paul R. Cohen
9/1990 – 5/1994University of Massachusetts, Amherst
B.S., Computer Science, Summa Cum Laude
Professional Experience
1/2006 – present Research Associate
Department of Computer Science & Electrical Engineering
University of Maryland Baltimore County
Primary responsibility was design and development of the Meta
Cognitive Loop, a domain-general metareasoning system intended
to make intelligent systems more robust by allowing them to
reason about and recover from unexpected failures. Additional
research programs include computational finance and bootstrapped
learning.
12/2004 – 12/2005Postdoctoral Research Fellow
Department of Astronomy
University of Massachusetts, Amherst
Involved in the design and development of monitor and control
software for the Large Millimeter Telescope and related projects.
Projects included real-time, networking, and user interface tools
for use on a 50m diameter millimeter-wave telescope under
construction in Puebla, Mexico, as well as design and developmentbootstrapped
for monitor and control software for other instruments under
development at the university.
10/2004 – 12/2004Postdoctoral Research Fellow
Experimental Knowledge Systems Lab
University of Massachusetts, Amherst
I was involved in an intensive 3-month rolling start to DARPA’s
“Integrated Battle Command” program. The program involved
integrating a handful of intelligent tools into a military planning
setting to improve efficiency and performance. Our tool was a
social simulation that projected long-term effects of military
courses of action in regions where insurgent or terrorist activity
was likely. The program concluded with a 4-day demo in which we
presented and used our tool in a live planning scenario.
9/1995 – 5/2004Research Assistant
Experimental Knowledge Systems Lab
University of Massachusetts, Amherst
I was involved in a variety of research projects in a
multidisciplinary AI lab. Projects drew heavily from the areas of
machine learning, intelligent data analysis, data mining,
simulation, and planning. The majority of my work was on a
project aimed at understanding the development of activity in
intelligent agents, and included work with both simulated agents
and the Pioneer-2 mobile robot.
6/1994 – 8/1995Systems Programmer
Experimental Knowledge Systems Lab
University of Massachusetts, Amherst
I was the primary developer of a Macintosh interface to CLASP, a
statistical analysis package developed in-house at the EKSL. I also
extended the hypothesis testing and contingency table analysis
components of this software.
Teaching Experience
Instructor for CS120 – Introduction to the Internet, University of Massachusetts,
Amherst. Summer 1999. Responsible for design, instruction, and grading of
intensive internet course taken by a mix of university students, continuing
education students, and gifted high school students.
Consultant for CS201 – Introduction to Assembly Language Programming,
University of Massachusetts, Amherst. Fall 1992. Assisted students in
understanding and writing of x086 assembly language programs. Publications
Conference Proceedings
Gary. W. King, Matthew D. Schmill, Andrew Hannon, and Paul Cohen. "The
Asymmetric Threat Assessment Tool (ATAT)". In Proceedings of the 14th
Conference on Behavior Representation in Modeling and Simulation (BRIMS) Orlando, FL, May 2005. L. Allender and T. Kelley, Eds.
Schmill, Matthew D., and Paul R. Cohen. 2002. A Motivational System That
Drives the Development of Activity. Proceedings of the Sixth International
Conference on Autonomous Agents and Multi-Agent Systems (AAMAS).
Lavrenko, V., Matthew D. Schmill, Dawn Lawrie, Paul Ogilvie, David Jensen, and James Allan. 2000. Language Models for Financial News Recommendation, Proceedings of the Ninth International Conference on Information and
Knowledge Management (CIKM).
Oates, Tim, Matthew D. Schmill, Paul R. Cohen. 2000. A Method for Clustering the Experiences of a Mobile Robot that Accords with Human Judgements.
Proceedings of the Seventeenth International Conference on Artificial
Intelligence.
Schmill, Matthew D,  Tim Oates and Paul R. Cohen. 2000. Learning Planning
Operators in Real-World, Partially Observable Environments. Proceedings of the Fifth International Conference on Artificial Intelligence Planning and
Scheduling.
Oates, Tim, Matthew D. Schmill and Paul R. Cohen. 1999. Efficient Mining of Statistical Dependencies. Proceedings of the Sixteenth International Joint
Conference on Artificial Intelligence.
Oates, Tim, Matthew Schmill and Paul R. Cohen. 1999. Identifying Qualitatively Different Outcomes of Actions: Gaining Autonomy Through Learning. The
Fourth International Conference on Autonomous Agents.
Schmill, Matthew D., Michael T. Rosenstein, Paul R. Cohen, and Paul Utgoff.
1998. Learning What is Relevant to the Effects of Actions for a Mobile Robot.
Proceedings of the Second International Conference on Autonomous Agents, pp.
247-253.
Jensen, David and Matthew D. Schmill. 1997. Accounting for Multiple
Comparisons in Decision Tree Pruning. Proceedings of the Third International Conference on Knowledge Discovery and Data Mining.
Oates, Tim, Matthew D. Schmill, and Paul R. Cohen. 1996. Parallel and
Distributed Search for Structure in Multivariate Time Series. Proceedings of the Ninth European Conference on Machine Learning.
Schmill, Matthew D., Tim Oates and Paul R. Cohen. 1995. Tools for Detecting Dependencies in AI Systems. In Proceedings of the Seventh International IEEE Conference on Tools with Artificial Intelligence.
Book Chapters
Oates, Tim, Matthew D. Schmill, Dawn E. Gregory and Paul R. Cohen. 1995.
Detecting Complex Dependencies in Categorical Data. In Doug Fisher and Hans Lenz, editors, Finding Structure in Data: Artificial Intelligence and Statistics V.
Springer Verlag.
Workshops
Matthew D. Schmill, Darsana Josyula, Michael Anderson, Tim Oates, Don Perlis, and Scott Fults. "Ontologies for Reasoning about Failures in AI Systems". In
First International Workshop on Metareasoning in Agent-Based Systems, 2007.
Michael L. Anderson, Matthew D. Schmill, Tim Oates, Don Perlis, Darsana
Josyula, Dean Wright, and Shomir Wilson. "Toward Domain-Neutral Human-
Level Metacognition". In Proceedings of the Eighth International Symposium on Logical Formalizations of Commonsense Reasoning, 2007.
Lavrenko, V., Matthew D. Schmill, Dawn Lawrie, Paul Ogilvie, David Jensen, and James Allan. 2000. Mining of Concurrent Text and Time Series, In
Proceedings of t he Sixth ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining.
Oates, Tim, Matthew D. Schmill, and Paul R. Cohen. 1999. Identifying
Qualitatively Different Outcomes of Actions: Experiments with a Mobile Robot.
In Working Notes of the IJCAI-99 Workshop on Robot Action Planning,
Matthew D. Schmill, Tim Oates, and Paul R. Cohen. 1999. Learned Models for Continuous Planning. In The Preliminary Papers of the Seventh International
Workshop on Artificial Intelligence and Statistics.
Tim Oates, Matthew D. Schmill, Paul R. Cohen, and Casey Durfee. 1999.
Efficient Mining of Statistical Dependencies. In Preliminary Papers of the
Seventh International Workshop on Artificial Intelligence and Statistics, pages
133 – 141.
Oates, Tim, Matthew D. Schmill, David Jensen, and Paul R. Cohen. 1997. A
Family of Algorithms for Finding Temporal Structure in Data. The Preliminary Papers of the Sixth International Workshop on Artificial Intelligence and
Statistics.
M.T. Rosenstein, Paul R. Cohen, Matthew D. Schmill, and Marc S. Atkin. 1997.
Action representation, prediction and concepts. In Preliminary Papers of the
AAAI Workshop on Robots, Softbots, Immobots: Theories of Action, Planning and Control,
Technical Reports
Lavrenko, V., Matthew D. Schmill, Dawn Lawrie, Paul Ogilvie, David Jensen,
and James Allan. 2000. Information Mining of Concurrent News and Time Series Technical Report IR-203, Dept. of Computer Science, University of
Mass/Amherst.
Schmill, Matthew D. 1998. A Distributed Approach to Finding Complex
Dependencies in Data. Technical Report 98-13, Dept. of Computer Science,
University of Mass/Amherst.
Schmill, Matthew D. and Paul R. Cohen. 1995. Learning Predictive
Generalizations for Multiple Streams: An Incremental Algorithm. Technical
Report 95-55, Dept. of Computer Science, University of Mass/Amherst.
Other Documents
Schmill, Matthew D. 1998. The EKSL Saphira-Lisp System and ACL User's
Guide. EKSL Memorandum 98-32. University of Massachusetts at Amherst.
Schmill, Matthew D. 1996. User's Guide to the Real Agent Architecture. EKSL
Memorandum 97-31. University of Massachusetts at Amherst.
Presentations
“Ontologies for Reasoning about Failures in AI Systems”. In First International
Workshop on Metareasoning in Agent-Based Systems. May 2007.
“Learning Planning Operators in Real-World, Partially Observable
Environments”. Full presentation to The Fifth International Conference on
Artificial Intelligence Planning and Scheduling. May 2000.
“Learned Models for Continuous Planning”. Poster presented to The Seventh
International Workshop on Artificial Intelligence and Statistics. January 2000.
“Learning What is Relevant to the Effects of Actions for a Mobile Robot”. Full
presentation to The Second International Conference on Autonomous Agents.
May 1998.
“A Family of Algorithms for Finding Temporal Structure in Data”. Poster presented to The Sixth International Workshop on Artificial Intelligence and Statistics. January 1998.
Tools for Detecting Dependencies in AI Systems. Full presentation to The Seventh International IEEE Conference on Tools with Artificial Intelligence. November 1995.

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。