Student presentation

The goals of the student presentation are:

You should become the class expert on your topic
You will present a 40-minute lecture on the topic
Everyone in the class will read your source material
The audience is expected to participate in discussion led by the presenter

You should use overheads such as PowerPoint or similar. Your job as the presenter is to pull out the important points of the topic or paper and present them clearly for the audience. If some part of the source article is unclear, your job is to make it clear.

Here is a list of questions you should answer for yourself and your audience when you read the material you will present and when you give your presentation.

What are the main points?
What is the task that the authors are trying to accomplish?
What is new about this approach? How does it compare to existing methods?
What models and learning algorithms are used in the research?
How are the author's claims being evaluated -- using experiments, theoretically, other ways?
What are strong points of the topic/paper?
What are weak points of the topic/paper?

You should not try to answer these questions directly in the presentation (i.e. you should not say "The main point of the paper is... The author's new contribution is..."). Instead, you should highlight these things as you make your presentation.

Presentation requirements

Here is what is required for the person presenting:

Read the paper/chapter carefully (start immediately on this).
Develop slides to present the paper.
Meet with the instructor to go over the slides prior to the presentation.
Send your completed slides to the instructor on the day before your talk.

Everyone in the class is expected to read the source material that the presentation is based on.

Some guidelines

Here are some notes on giving a research talk, from Charles Elkan.

Here are some additional points, from your instructor.

Make sure you put some thought into choosing your paper, to minimize frustration later.
Choose a paper that looks interesting to you.
Present the research. If you talk about your opinion or something outside of what the paper claims, make sure you make that clear.
Use graphs that come from the source material.
Explain things for your audience. What might seem obvious to you after reading the paper will not be obvious for your audience.
Have fun with the presentation!

Evaluation

You will be evaluated according to the guidelines listed here, and will receive feedback by this feedback form.

Topics and schedule

Wednesday, April 19 (Josh): Learning hidden Markov model structure for information extraction (K. Seymore)
Friday, April 21 (Sean): Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods (J. Platt)
Monday, April 24 (Greg): Decision trees (Chapter 3 from Mitchell)
Wednesday, April 26 (Noah): A short introduction to boosting (Y. Freund and R. Schapire)
Friday, April 28 (Joe): On Feature Selection: Learning with Exponentially many Irrelevant Features as Training Examples (A. Ng)
Monday, May 1 (Bharat): Neural networks (Chapter 11.3 - 11.9 in our textbook)

valid html and css