STatistical AI Reading Group previous readings: Feb-May, 2001
- Feb 13, 2001 (stairmaster: Christian):
- Using All Your Experiences
(abstract)
- Feb 27, 2001 (stairmaster: Leslie):
- Schmidhuber, J. "Algorithmic Theories of Everything." Technical
Report IDSIA-29-00. Istituto Dalle Molle di Studi sull'Intelligenza
Artificiale, Dec 2000.
(Compressed
PostScript)
- Mar 6, 2001:
- Postponed due to weather. See you all next week!
- Mar 13, 2001 (stairmaster: Leslie):
- Reprise of Schmidhuber's "Algorithmic Theories of Everything,"
focusing on Sections 6 and 7.
(Compressed
PostScript)
- Mar 27, 2001:
- Spring break. Go find some sun or something. We won't be
here -- neither should you.
- Apr 3, 2001 (stairmaster: Terran):
- Webb, G. (1996). Further experimental evidence against the utility
of Occams razor. Journal of Artificial Intelligence
Research. 4: 397-417. (
PostScript)
- April 10:
- Cancelled due to sick stairmaster.
- Apr 17, 2001 (stairmaster: Christian):
- Freund, Y. and Schapire, R. E., Adaptive game playing using
multiplicative weights. Games and Economic Behavior,
29:79-103, 1999.
(
PostScript)
- April 24, 2001 (stairmaster: Terran):
- J. Yedidia, W. T. Freeman, and Y. Weiss Generalized Belief
Propagation To appear in: Advances in Neural Information Processing
Systems 13, 2001.
(PDF).
-
Related works:
-
W. T. Freeman and E. C. Pasztor Markov networks for
super-resolution. Published in Proceedings of 34th Annual
Conference on Information Sciences and Systems (CISS 2000),
Dept. Electrical Engineering, Princeton University, Princeton, NJ
08544-5263, March, 2000.
(PDF)
-
Y. Weiss and W. T. Freeman Correctness of Belief Propagation in
Gaussian Graphical Models of Arbitrary Topology. Also published
as UC Berkeley CS Department TR UCB//CSD-99-1046.
(PDF)
- May 8, 2001 (stairmaster: Terran/Erik):
- S. Amari and S.C. Douglas, Why Natural Gradient,
IEEE International Conf. Acoust., Speech, Signal Processing, Seattle,
WA, May 1998. (Not available online.)
- S. Amari, A. Cichocki, and H. H. Yang, A New Learning Algorithm for
Blind Signal Separation, In: Advances in Neural Information
Processing Systems 8, Editors D. Touretzky, M. Mozer, and M. Hasselmo,
pp. 752-763, MIT Press, Cambridge MA, 1996.
(
Compressed PostScript.)
- Shun-ichi Amari, Natural Gradient Works Efficiently in
Learning, Neural Computation, Vol.10, pp.251-276, 1998.
(
Compressed PostScript.)
- May 15, 2001 (SPECIAL LOCATION: NE43-516):
- Special meeting: talk by visiting scholar Georgios Theocharous
from Michigan State University.
Hierarchical Learning and Planning using
Partially Observable Markov Decision Processes
(Abstract)