Organizer: Jesse Davis (jdavis at cs) Meeting Time: 4:30-5:20 pm on Wednesday Location: 203 Mailing List: uw-ai at cs dot washington dot edu Quarter: Winter 2010 |
Each week one person will be responsible for picking a paper for the group to read. This individual will also lead the group discussion. Everyone who attends the meeting should read the paper and contribute to the discussion.
The goal of this quarter's reading group is discuss papers on foundation and trends papers (e.g., Yoshua Bengio's overview of deep learning) and structure learning.
The discussion leader should plan on presenting a 30-35 minute overview of the paper. The presentation does not need to be formal, i.e., no slides are needed. If we are discussing a conference paper, a good tactic is for the discussion leader to ask the author of the paper for the slides from the conference talk.
Discussion Leader | Paper | |
January 6th | Organizational meeting |   |
January 13th | Robert Gens | Learning Deep Architectures for AI by Bengio. Understand sections 1 - 3, 7, 9. Skim 4 and 5. |
January 20th | Stef Schoenmackers | Required reading: The FOIL paper by Ross Quinlan. Recommended reading: The Progol paper by Stephen Muggleton |
January 27th | Rina Dechter, UC Irvine | TBD |
February 3th | Tony Fader | Active learning overview by Burr Settles |
February 10th | Andrew Guillory | Rui Castro, Charles Kalish, Robert Nowak, Ruichen Qian, Timothy Rogers, and Xiaojin Zhu. Human active learning.* In Advances in Neural InformationProcessing Systems (NIPS) 22, 2008. |
February 17th | Janara Christensen | P. Donmez, J. Carbonell and J. Schneider, Efficiently Learning the Accuracy of Labeling Sources for Selective Sampling. In Proceedings of KDD 2009 |
February 24th | Kevin Lai | Gregory Druck, Burr Settles, Andrew McCallum, Active Learning by Labeling Features, EMNLP 2009. Available here |
March 3rd | Danny Wyatt | |
March 10th | Congle Zhang | Latent Dirichlet Allocations |