The Fourth Bayesian
Modelling Applications Workshop
during UAI 2006
July 13th, 2006
Cambridge,
MA, USA
Special
theme: Bayesian Models
meet Cognition
Contents
Workshop
program
09:00
- 09:10 Welcome
Moderator: Linda C.
van der Gaag
09:10 - 10:40 Session I: Human factors
in output
Moderator: Kathryn B.
Laskey
10:40
- 11:00 Coffee
break
11:00 - 12:30
Session II: Modelling human factors
Moderator:Judy
Goldsmith
"Modeling
Human Reasoning about Meta-Information"
Sean
Guarino, Jonathan Pfautz, Zach Cox, and Emilie Roth
"Bayesian
Model of the Effect of
Personality in Predicting Decisionmaker Behavior"
Paul
J. Sticha, Dennis M. Buede, and Richard L. Rees
"Applications
of Bayesian Belief Networks in Social Network Analysis"
David
Koelle, Jonathan Pfautz, Michael Farry, Zach Cox, Geoffrey Catto,
and Joseph Campolongo
12:30
- 14:00
Lunch
14:00
- 15:30 Session III: Human factors in construction and maintenance
Moderator:TBA
"Bayesian
Ontologies in AI Systems"
Paulo
C. G. da Costa, Kathryn B. Laskey, and Ghazi AlGhamdi
"Automated
Knowledge Elicitation and Flowchart Optimization for Problem Diagnosis"
Alina
Beygelzimer, Mark Brodie, Jonathan Lenchner, and Irina Rish
"A
Benchmark Model for Decision-Theoretic Planning with Constraints"
Kendra
Renee Gehlbach, Brandon Laracuente, Cynthia Isenhour, Judy
Goldsmith, Beth Goldstein, and Miroslaw Truszczynski
15:30 - 15:50 Coffee
break
15:50 - 16:50 Session IV: Human
factors through the engineering process
Moderator:Russell
Almond
16:50 - 18:00
Discussion and closing
Moderator: Linda C.
van der Gaag
[back to top]
The workshop
proceedings, containing the papers presented at the workshop, can be
found here.
[back
to top]
The UAI 2006
conference will be held at Massachusetts Institute of Technology (MIT),
Cambridge, MA, USA. The Bayesian Modelling Applications Workshop is
going
to be located in room E51-145, which is
located in the Tang Center, the same building as the main
conference (see http://whereis.mit.edu/map-jpg?mapterms=e51&mapsearch=go). It
is on the 2nd level (as is the main conference). The entrance to use
is the one located on 2 Amherst Street (on the corner of
Wadsworth and Amherst Street).
[back
to top]
Call for contributions
Goal
As in the previous years, the
goal of the workshop is to provide a focused,
informal forum for a fruitful exchange of research questions and
insights, of experiences, and of methodologies and techniques among
theorists, practitioners and tool developers in the application of
Bayesian models to a wide range of application areas. As an
additional avenue of exchange, eligible contributions will be compiled
into proceedings in addition to the overall conference publication.
Based on the response at the workshop, papers will be selected for
later publication in a special handbook or journal issue.
Special topic area
This year we are
especially encouraging contributions that address our special theme Bayesian
models meet Cognition. In particular,
we are looking for papers that focus on issues in the application of
Bayesian models that involve human factors. Examples include, but are
not restricted to, the following issues.
In the construction of a
Bayesian model, often both its graphical structure
and its associated numerical parameters are acquired from human
experts.
For this purpose, dedicated elicitation techniques are being designed.
Do these techniques forestall, for example, biases and
over-commitments of the resulting model? Are these techniques easy to
use, taking relatively little time on the part of the experts?
Do the techniques scale up to building large models? How can knowledge
obtained from multiple experts be combined? How
can experts be involved in assessing the quality of the resulting
model?
Bayesian models
usually are developed with a "real world" setting in mind and are
tailored to this setting. The model will be consulted by users who have
to enter data, to understand the output, to assess the validity and
robustness of the output, and to receive support in their reasoning
and decision-making processes. How can data entry be organised and
supported, to allow for easy use of the model? How can the output of
the model be presented to the user, to allow for easy and correct
interpretation? How can the output of the model be explained to the
user? How can the model support "what-if" reasoning processes?
General focus
The emphasis of
this year's workshop is on cognitive issues that have to be
addressed when developing and using Bayesian models. We are encouraging
submissions that address fundamental issues, present concrete
solutions, describe experiments, or analyse open problems, within a
broad
range of application areas involving diagnosis, optimisation,
temporal reasoning, spatial reasoning, and forecasting.
In addition to
submissions addressing human factors, we also welcome contributions to
the overall focus of Bayesian modelling. Submissions addressing novel
applications are particularly encouraged.
Format
The workshop
will take place on Thursday, July 13th, the day of the UAI tutorials.
The workshop will begin with each participant giving a short
introduction to themselves and their work. These brief introductions
will be followed by sessions devoted to cognitive issues in
developing and using Bayesian models, consisting of presentations
and open discussions. We will conclude with a plenary panel discussion
which will sum up the days activities and talk about possible plans
for next year.
Arrangements
The workshop
will run on the premises of the general UAI conference. A registration
fee for the workshop will be required in addition to the main
conference registration.
To contribute
Persons desiring
to contribute should prepare a contribution (3 - 8 pages, preferrably
in the same format as for the overall conference) and a short statement
of interest, explaining their background, the applications in
which they have contributed and the characteristics of the domain in
which they work. The contribution should raise questions and
offer results, which the participant can speak about. All participants
will be expected to have material to present for the workshop.
Participants are encouraged to apply jointly with members of other
disciplines with whom they have collaborated. Send all submissions
and enquires to uai-workshop [at] cs.uu.nl.
Participation will be limited
to 30 individuals. All members of the workshop
committee who would like to attend are expected to qualify as
participants.
Selection will be done by the committee's decision of the mix of
individuals who are likely to generate the most constructive
presentations
and discussions.
Workshop committee
Linda van der
Gaag, Utrecht University, Chair
Russell Almond, Educational Testing Service, Co-Chair
John
Mark Agosta, Intel Corporation, Chair Emeritus
Marek Druzdzel,
University of Pittsburgh
Judy Goldsmith,
University of Kentucky
Oscar Kipersztok, The Boeing Company
Kathryn Blackmond Laskey,
George Mason University
Hermi Schijf,
Utrecht University
Important dates
Submission of contributions:
April 21st, 2006
Notification of selections by the organising committee: May 12th, 2006
Deadline for contributions to the proceedings: June 23rd, 2006
Date of the workshop: July 13th, 2006
Previous editions
The
Third Bayesian Modeling Applications Workshop, during UAI-05.
The Second
Bayesian Modeling Applications Workshop, during UAI-04.
Bayesian
Modeling Applications Workshop, during UAI-03.
Contact
Send all enquiries and
submissions to: uai-workshop [at] cs.uu.nl.
Last updated: July 6 2006 by Eveline Helsper