Fall 2005 Reading Group

 This group meets weekly to discuss papers in the areas of statistical artificial intelligence, machine learning, and robotics. Topics of special interest for fall 2005 include discriminative vs generative models and object identity/data association frameworks.

Meeting time: Fridays at 2:30 pm.

Meeting location: Paul Allen Centre 491

Meeting schedule

• September 30th:
  Introductory meeting. No readings.
• October 7th:
  Discussion of On Discriminative vs. Generative Classifiers: A comparison of logistic regression and Naive Bayes, Andrew Y. Ng and Michael Jordan. In NIPS 14, 2002.
• October 14th:
  Discussion of BLOG: Probabilistic Models with Unknown Objects, Brian Milch, Bhaskara Marthi, Stuart Russell, David Sontag, Daniel L. Ong, and Andrey Kolobov, Proc. 19th International Joint Conference on Artificial Intelligence (IJCAI): 1352-1359, 2005.
• October 21st:
  Presentation of Object Identification with Attribute-Mediated Dependences, by Parag Singla and Pedro Domingos, PKDD-05... by the first author, Parag Sigla.
• October 28th:
  Discussion of Practical Markov Logic Containing First-order Quantifiers with Application to Identity Uncertainty, by Aron Culotta and Andrew McCallum.
• November 4th:
  No meeting.
• November 11th (Moved to November 10th, 12-1:30:
  Discussion of Combining SVM with graphical models for supervised classification: an introduction to Max-Margin Markov Networks by Simon Lacoste-Julien. Tech Report.
• November 18th:
  Discussion of Bayesian Inference in the Space of Topological Maps by Ranganathan, Menegatti, and Dellaert.
• November 25th:
  Thanksgiving break
• December 2nd:
  Discussion of A Conditional Model of Deduplication for Multi-Type Relational Data, by Aron Culotta and Andrew McCallum.

Some papers of possible interest: