U of S |
CS Home |
Mike's Home
Michael C. Horsch -- at work
I am interested in
reasoning under uncertainty and constraint satisfaction.
An underlying theme of my current research is meta-reasoning: the
formalization of the trade-offs between the cost of computation and the
value of result of computation, and the explicit use of computation at
the meta-level to decide how to get the most value from computational
resources. I am also interested in inference methods for Bayesian networks
and constraint satisfaction, path planning, and practical applications of AI.
Publications |
Links
-
Kevin Grant
and M. C. Horsch.
``Exploiting Dynamic Independence in a Static Conditioning Graph.''
In Proceedings of the Nineteenth Canadian
Conference on Artificial Intelligence, June 2006, Laval, Canada, 12
pages.
PDF
-
Kevin Grant
and M. C. Horsch.
"Methods for Constructing Balanced
Elimination Trees and Other Recursive Decompositions."
In Proceedings
of the Nineteenth Florida Artificial Intelligence Research Society
(FLAIRS) Conference, May 2006, Melbourne Beach, USA, 6 pages.
PDF
- Jeff R. Long, Michael C. Horsch
"A Formalization of Game Balance Principles."
In
Workshop on Game Theory, Machine Learning and Reasoning
under Uncertainty, 19th Annual Conference on Neural Information
Processing Systems, December, 2004, Whistler, Canada, 8 pages.
-
Kevin Grant,
Michael C. Horsch, "Practical Structures for
Inference in Bayesian Networks." In 18th Australian Joint Conference on Artificial
Intelligence December 2005,
Sydney.
PDF
- Michael C. Horsch, Jingfang Zheng
"A Decision Theoretic
Meta-Reasoner for Constraint
Optimization. In Proceedings of the Eighteenth Canadian
Conference on Artificial Intelligence, Victoria, British Columbia,
2004, pp53-65.
PDF
- Jeff R. Long, Michael C. Horsch
"A Bayesian model to smooth telepointer jitter."
In
Proceedings of the Eighteenth Canadian Conference on Artificial
Intelligence, Victoria, British Columbia, 2004, pp 108-119.
PDF
- David Mould, Michael C. Horsch, "An Hierarchical Terrain
Representation for Approximately Shortest Paths"
In Proceedings of the Eighth Pacific Rim
International Confer-
ence on Artificial Intelligence, August 2004, Auckland, pp. 104-113
PDF
- Jingfang Zheng, Michael C. Horsch, "A Comparison of Consistency
Propagation Algorithms in Constraint Optimization." In Proceedings of the
Sixteenth Canadian Conference on Artificial Intelligence, June 2003, Halifax, pp. 160-174
PDF
- Kevin Grant, David Mould, Michael Horsch, Eric Neufeld, "Enhancing
Demosaicking Algorithms using Loopy Propagation." In Proceedings of the
Fifth International
Conference on Computer Graphics and Artificial Intelligence. May 2003,
Limoges
(FRANCE), pp. 129-142
postscript
-
Vassileva, J.
Breban, S. Horsch M. "Agent Reasoning Mechanism for Long-Term
Coalitions Based on Decision Making and Trust." Computational Intelligence, 18, 4,
583-595, November 2002 Special Issue on Agent Mediated Electronic Commerce.
PDF
- Michael C. Horsch, William
S. Havens, Aditya K. Ghose. "Generalized
Arc Consistency
with Application to MaxCSP and SCSP Instances." In Proceedings of
the Fifteenth
Canadian Conference on Artificial Intelligence, May 2002, Calgary,
pp 104--118.
PDF
-
Michael C. Horsch and William S. Havens.
Probabilistic
Arc Consistency: A connection between constraint reasoning and
probabilistic reasoning. In Proceedings of the Sixteenth Conference
on Uncertainty in Artificial Intelligence, pages 282-290, 2000.
compressed postscript
-
Michael C. Horsch and William S. Havens.
An empirical evaluation
of Probabilistic Arc Consistency as a variable ordering heuristic:
Extended Abstract. In Sixth International Conference on Principles
and Practice of Constraint Programming.
compressed postscript
-
Michael C. Horsch and David Poole.
Estimating the Value of Computation in
Flexible Information Refinement. In Proceedings of the Fifteenth
Conference in Uncertainty in Artificial Intelligence, 1999.
compressed postscript
-
Michael C. Horsch and David Poole.
An Anytime Algorithm for Decision
Making under Uncertainty. In Proceedings of the Fourteenth Conference in
Uncertainty in Artificial Intelligence, 1998.
postscript
-
Michael C. Horsch and David Poole.
Flexible Policy Construction by
Information Refinement. In Proceedings of the Twelfth Conference in
Uncertainty in Artificial Intelligence, 1996.
postscript
-
Michael C. Horsch and David Poole.
A dynamic approach to probabilistic
inference using Bayesian networks. In Proceedings of the Sixth Conference in
Uncertainty in Artificial Intelligence, 1990.
-
Michael C. Horsch. "Flexible Policy Construction by Information Refinement."
PhD Thesis, University of British Columbia, 1998.
postscript
© 2000-2004, Michael C. Horsch, horsch@cs.usask.ca
This page last modified Tuesday November 21, 2006