CIS 620 - Spring 2007
A list of presenters can be found here.
The presentations are the second most significant part of your grade in this class
(30%), and provide an additional way to gain a deeper understanding of
a specific topic. Please send three (3) suggestions for papers you would like to present to cis620@seas. We will select among your suggestions and assign a date for you present to maximize continuity and minimize overlap between presentations.
- Paper selection: Tuesday, March 20. Email cis620@seas.
- Slides: Two days before your talk. Meet with instructors.
- Presentation: In Class.
- Tuesday, March 27.
- Thursday, March 29.
- Tuesday, April 3.
- Thursday, April 5.
- Tuesday, April 10.
- Thursday, April 12.
- Tuesday, April 17.
There are four themes which cover a broad range of topics of interest, so
it should easy to choose a paper that fits well within these themes. It can be a short
conference paper or a long journal paper. Each presentation will be
twenty minutes long (20) with an additional five minutes (5) for
questions and comments. You should decide what part or the paper you want to present. (For example the details of an algorithm? analysis? specific set of experiments?).
You should use slides for the presentation (your favorite application). At
least two days before your presentation (Friday if you present on
Tuesday, Tuesday if you present on Thursday), you should meet with one
of us to discuss the slides and presentation.
You can choose to present either a conference paper or a
journal paper. UAI (http://www.auai.org/) , NIPS (http://nips.cc/) and ICML are three of the
main computer science conferences where graphical models work is
published, with many of the recent papers online. Of course,
conferences on computer vision, natural language processing,
computational biology, sensor networks, and many others have a lot of
graphical model papers as well. JMLR (http://www.jmlr.org/) is a main
relevant online journal, but there are many more, printed or
electronic, available through the library.
There are four themes. Some of them overlap with the material
taught in class and provide a way to gain a deeper understanding in
a specific subject; some are about new material
- Approximate Inference: Presenting one of the many techniques not taught in class.
- Semisupervised and Unsupervised Learning: Learning with indirect feedback in the context of graphical model is challenging and an open field of research.
- Structured Prediction: Learning models for making multiple, related predictions at once. Representative examples include pixel-labeling we discussed in class or parsing a sentence, where the input is a sentence, and the output is a parse
tree of a sentence.
- Application: The tools presented in class are used
in many domains: natural language processing, speech analysis, image
processing and others. Present a specific application with the approach
used to solve the problem. Why did the methods work well?
We will evaluate your presentations according to the following four criteria:
- Content: Is a good range of information included (not too obvious nor too specialized)? Are the main points covered?
- Delivery: Is the presentation clear and concise?
- Organization: Is the talk well-structured? Easy to follow?
Some example papers:
Unsupervised and Semisupervised Learning: