|
Organizer: Jesse Davis (jdavis at cs) Meeting Time: 5:30-6:20 pm on Tuesdays Location: 503 Mailing List: mlread at cs dot washington dot edu Quarter: Autumn 2009 |
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 from the summer conferences. We are particularly interested in covering papers related to lifted inference and deep learning (i.e., deep belief networks). Discussion leaders should try to pick papers that will have wide appeal.
The discussion leader should plan on presenting a 25-30 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 | |
| October 6th | Chloe Kiddon | Rodrigo de Salvo Braz, Sriraam Natarajan, Hung Bui, Jude Shavlik and Stuart Russell. Anytime Lifted Belief Propagation, SRL 2009 |
| October 13th | Aniruddh Nath | Kristian Kersting, Babak Ahmadi and Sriraam Natarajan. Counting Belief Propagation, UAI 2009 |
| October 20th | Robert Gens | Honglak Lee, Roger Grosse, Rajesh Ranganath and Andrew Ng. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, ICML 2009 |
| October 27th | Evan Herbst | Chun-Nam John Yu and Thorsten Joachims. Learning Structural SVMs with Latent Variables, ICML 2009 |
| November 3th | Andrey Kolobov | Geoffrey Gordon, Sue Ann Hong and Miroslav Dudik. First-Order Mixed Integer Linear Programming, UAI 2009 |
| November 10th | Stanley Kok | Jude Shavlik and Sriraam Natarajan. Speeding Up Inference in Markov Logic Networks by Preprocessing to Reduce the Size of the Resulting Grounded Network, IJCAI 2009 |
| November 17th | Galen Andrew | Max Welling. Herding Dynamical Weights to Learn, ICML 2009 Max Welling. Herding Dynamic Weights for Partially Observed Random Field Models, UAI 2009 |
| November 24th | Tony Fader | Sushmita Roy, Terran Lane and Margaret Werner-Washburne. Learning structurally consistent undirected probabilistic graphical models, ICML 2009 |
| December 1st | No class! | |
| December 8th | Alan Ritter | Iain Murray and Ruslan Salakhutdinov, Evaluating probabilities under high-dimensional latent variable models, NIPS 2009 |