Call for
Papers
Topics
Organizing
Committee
Program
Committee
Dates
Topics
Submission
Accepted Papers
Workshop Program
CFP in pdf
MetaReasoning Links |
|
Call for Papers
The 21st century is experiencing a renewed interest in an old idea within
artificial intelligence that goes to the heart of what it means to be both human
and intelligent. This idea is that much can be gained by thinking of one's own
thinking. Metareasoning is the process of reasoning about reasoning itself. As
shown below, it is composed of both meta-level control of computational
activities and the introspective monitoring of reasoning to evaluate and to
explain computation. Meta-level control is the ability of an agent to
efficiently trade off its resources between object level actions (computations)
and ground level actions to maximize the quality of its decisions. Introspective
monitoring is necessary to gather sufficient information with which to make
effective meta-level control decisions or to explain failed object-level
reasoning. This workshop will explore the implications of this model by
examining the various aspects of metareasoning and models of self and their role
in single-agent and multiagent applications.
This one-day workshop will focus on techniques and benefits of metareasoning and
introspection in self adaptive systems. It will include a number of short paper
presentations, thematically organized discussion sessions, and a keynote address
by Dr. Mike Cox, DARPA. We also will include panel discussions so that the audience can ask
follow up questions that compare and contrast related positions.
Potential Topics:
• Theoretical models of metareasoning
• The integration of meta-level control and monitoring
• Multiagent coordinated metareasoning
• Meta-explanation and self-explanation
• Self-adaptive systems and autonomic computing
• Centralized versus distributed meta-level control
• Human metacognition and metamemory
• The role of state abstraction in metareasoning
• Computational models of self and consciousness
• Logical introspection and reflective logic programming
• Bounded rationality
• Learning agents and metareasoning
• Evaluation of metareasoning systems
Organizing Committee:
Robert Laddaga (co-chair)
Anita Raja (co-chair)
Senior Research Scientist
Associate Professor
Intelligent Computing
Department of Software & Information Systems
BBN Technologies
University of North Carolina at Charlotte
Cambridge, MA 02138
Charlotte, NC 28223
rladdaga@bbn.com
anraja@uncc.edu
(617) 873-5524
(704) 687-8651
Michael L. Anderson, Assistant Professor. Franklin & Marshall
College.
Howard Shrobe, Principal Research Scientist, MIT.
Shlomo Zilberstein, Professor, University of Massachusetts.
Program Committee:
Mark Burstein, Principal Scientist, BBN.
Robert Goldman, Principal Researcher, SIFT, LLC.
Victor Lesser, Professor, University of Massachusetts.
John Maraist, Senior Scientist, SIFT, LLC.
David Musliner, Principal Researcher, SIFT, LLC.
Paul Robertson, Senior Research Scientist, BBN.
Important Dates:
|
Submission Deadline |
July 10, 2009
July 17, 2009* |
|
Acceptance Notification |
August 5, 2009 |
|
Camera-ready Copy |
August 15, 2009 |
|
SASO Workshop |
September 15, 2009 |
Submission Instructions:
We encourage the submission of
high quality, original papers that are not submitted for publication elsewhere.
All submissions should be 10 pages formatted according to the IEEE Computer
Society Press proceedings style guide 8.5" x 11" Two-Column Format. Document
templates for submissions can be downloaded
here. Short position statements are also accepted. Submissions should be
emailed to both chairs (rladdaga@bbn.com and anraja@uncc.edu) by the deadline
period.
Accepted Papers:
Metacognition for
Self-Regulated Learning in a Dynamic Environment,
Darsana P. Josyula, Franklin C. Hughes, Harish Vadali, Bette J. Donahue,
Fassil Molla, Michelle Snowden, Jalissa Miles, Ahmed Kamara and Chinomnso
Maduka
Funk2: A Distributed
Processing Language for Reflective Tracing of a Large Critic-Selector
Cognitive Architecture
Bo Morgan
Metareasoning-based Self
Adaptive Tracking
Paul Robertson and Robert Laddaga
Priority-based
Meta-Control within Hierarchical Task Network Planning
Robert Goldman and David Musliner
Influencing Massive
Multi-agent Systems via Viral Trait Spreading
Brian Mclaughlan and Henry Hexmoor
Metareasoning-based Learning
for Classification Hierarchies
Joshua Jones & Ashok Goel
Learning from Observing:
Vision and POIROT Using Metareasoning for Self Adaptation
Mark Burstein, Robert Bobrow, William Ferguson, Robert Laddaga, Paul
Robertson
Position Papers:
Prediction and Metacognition
James L Eilbert
The Logical Road to Human Level AI Leads to a Dead End Compassionate
Intelligence and Affective Inference Cindy Mason
Workshop Program:
Tentative Schedule
|
9 am |
Introduction |
| 9:30
am |
Keynote: Computational Introspection, Mike Cox
[pdf] |
|
10:30 am
|
Break |
|
10:45 am
|
Metacognition
for Self-Regulated Learning in a Dynamic Environment, Josyula et al. |
|
11:15 am
|
Funk2: A
Distributed Processing Language for Reflective Tracing of a Large
Critic-Selector Cognitive Architecture, Bo Morgan |
|
11:45 am
|
Metareasoning-based
Self Adaptive Tracking - Robertson and Laddaga [pdf] |
|
12:15 pm
|
Lunch |
|
1:30 pm
|
Priority-based
Meta-Control within Hierarchical Task Network Planning, Goldman and Musliner
[pdf] |
|
2:00 pm
|
Influencing
Massive Multi-agent Systems via Viral Trait Spreading Mclaughlan and
Hexmoor |
|
2:30 pm
|
Metareasoning-based
Learning for Classification Hierarchies, Jones & Goel [pdf] |
|
3:00 pm
|
Learning from
Observing: Vision and POIROT Using Metareasoning for Self Adaptation,
Burstein et al. |
|
3:30 pm
|
Poster
Presentations: Eilbert |
|
3:45 pm
|
Discussion
Panel |
Links:
*After several requests,
the due date for workshop papers has been extended to 17 July 2009. We cannot
postpone further because the conference hasn't postponed the date we must
provide them with decisions. If you can submit your paper on the 10th we'd
appreciate it. If you intend to use the extension, please send us an email
indicating your intention. Either way, we would like to know by friday 10 July
if you plan to submit by the 17th.
|