Welcome to the Machine Learning Reading Group at Brown University. We will meet Wednesdays at 1pm in the CIT library (on floor 4).

MLRG meetings and other news are announced via posts to the ML-READING-GROUP list. You can subscribe at The MLRG leader this semester is Micha Elsner.

This term we will continue our organization from last semester, looking into 3 or 4 topics in depth, in 3-4 week sessions. Our topics will be Online and Active Learning, Boosting and Variational Methods. (Sorry-- I really wanted to get to variational methods, but we didn't. Maybe next year.)

Date Topic Important People
Jan 31 Finish Up Belief Propagation
Constructing free-energy approximations and generalized belief propagation algorithms
Topic Leader: Stefan Roth
Feb 7 Organizational Meeting Everyone
Feb 14 Online and Active Learning Intro (Lubrano)
20 Questions
A Note on the Utility of Incremental Learning
Locally Weighted Projection Regression: An O(n) Algorithm for Incremental Real Time Learning in High Dimensional Space
Dan, Jonas
Feb 21 Locally Weighted Projection Regression: Is it Any Good?
Fast and Efficient Incremental Learning for High-Dimensional Movement Systems (6 pgs)
Incremental Online Learning in High Dimensions (33 pgs)
LWPR code (C++ and Matlab)
Dan, Jonas
Feb 28 Sparse Online Gaussian Processes
Sparse Online Gaussian Processes
Dan, Jonas
March 7 Object Categorization (Rob Fergus)
One-Shot Learning of Object Categories
job talk: Monday, March 12 (noon)
grad student meeting: March 12 (4pm)
March 14 Example-based Learning (Gregory Shakhnarovich)
Fast Pose Estimation With Parameter-sensitive Hashing
job talk: Wednesday, March 14 (noon)
grad student meeting: March 14 (4pm)
March 21 Energy-based Component Analysis (Room 368)
No paper to read yet!
Fernando De la Torre (outside speaker, host Michael Black)
March 28 No meeting.
April 4 Bayesian Latent Variable Models (Ricardo Silva)
Towards association rules with hidden variables
job talk: Monday, April 2 (noon)
grad student meeting: April 2 (4pm)
April 11 Comparing Clusters With Information Theory
Comparing Clusterings (8 pgs)
Comparing Clusterings-- An Information-based Distance (41 pgs)
April 18 Boosting: Adaboost and Extensions
Improved Boosting Algorithms Using Confidence-rated Predictions
April 25 Generalization Performance of Adaboost and Extensions
continue to read Improved Boosting Algorithms Using Confidence-rated Predictions
May 2 Canceled
May 9 Multi-label Adaboost
continue to read Improved Boosting Algorithms Using Confidence-rated Predictions
Greg, or Sung-Phil, or everyone!

Links: Computational Modeling Reading Group (alternate Fridays, 10am)