STatistical AI Reading Group previous readings: February-May, 2005
- February 11th-18th (Stairmaster: Hanna):
-
- Parameter learning of logic programs for
symbolic-statistical modeling, by Sato, T. and Kameya, Y., JAIR 2001.
- A dynamic programming approach to parameter learning of generative models with failure., by Sato, T. and Kameya, Y., Proceedings of ICML Workshop on Statistical Relational Learning, 2004.
- February 25th (Stairmaster: Luke):
-
- The Statistical Approach to the Design of Spoken Dialogue
Systems, by S. Young. Tech Report CUED/F-INFENG/TR.433, Cambridge University Engineering
Department.
- March 4th (Stairmaster: Yu-han):
-
- Online bounds for Bayesian Algorithms, by Sham Kakade and Andrew Ng, NIPS-2004/5.
- March 11th (Stairmaster: Hanna):
-
- Conditional Models of Identity Uncertainty with Application to Noun
Coreference, by Andrew McCallum and Ben Wellner, NIPS 2004
- March 18th (Stairmaster: Yu-han):
-
- Online bounds for Bayesian Algorithms, by Sham Kakade and Andrew Ng, NIPS-2004/5.
- March 25th : Spring Break
-
- April 1st (Stairmaster: Natalia):
-
- Graph kernels and Gaussian processes for relational reinforcement
learning, by Thomas Gartner, Kurt Driessens, and Jan Ramon.
- April 8th (Stairmasters: Luiz and Natalia):
-
- Introduction to Gaussian Processes, by D.J.C. MacKay.
- April 15th (Stairmaster: Mike):
-
- Tree-Based Reparameterization Framework for Analysis of Sum-Product and
Related Algorithms, by Martin Wainwright, Tommi Jaakkola, and Alan
Willsky (IEEE Transactions on Information Theory, May 2003)
- April 29th (Stairmaster: John):
-
-
Hierarchical Dirichlet Processes,
by Y.W. Teh, M.I. Jordan, M.J. Beal and D.M. Blei. Technical Report 653, UC
Berkeley Statistics, 2004.
- May 6th (Stairmaster: John):
-
...the same as the previous week.
- May 13th (Stairmaster: Luke):
-
-
Learning Partially Observable Deterministic Action Models,
by E. Amir, in 19th Intl' Joint Conference on Artificial Intelligence (IJCAI'05).
- May 27th (Stairmaster: Emma):
-
-
A Biologically Plausible Algorithm for Reinforcement-Shaped Representational Learning, by Maneesh Sahani.