Discussions and paper reviews

The quality of our discussions will rely on how prepared everyone is when they come to class. It is important to do the reading in order to actively participate. To assist in this preparation, before coming to class students are required to submit a paper review on one of the assigned papers. A good review includes a brief synopsis of the paper content, a thoughtful analysis of its contributions and strengths/weaknesses, and notes about points that are unclear.

When writing paper reviews for this class, please address the following points (in any order):

· Give a brief (2-3 sentences) summary of the paper in your own words.

· What appears to be the main contribution of the paper?

· What are the paper’s primary strengths? weaknesses? (These may refer to both technical strategies and clarity.)

· How convincing are the experiments? If they appear lacking in some way, what would you suggest be tested?

· Are there any obvious (or less obvious) ways this work could be extended?

· Any additional comments, including questions it raises for you, or points that are not clear.

A few examples of good paper reviews are here.

Reviews are due via email by 10 PM on the night before class (Thursday). Please send the review as the text of an email (no attachments), and put the class date and author name in the subject of the email (e.g., Review for 2/1: Smith et al.). In weeks that you are presenting or giving a demo, it is not necessary to write a review.

Presentations

Each student will give a presentation in class on a topic chosen from this list. This presentation should overview work done in the area, synthesize any underlying commonalities of various approaches, and highlight interesting distinctions. The goal is to become familiar with the background and existing work in this particular area, and to relay it to the class with a polished, well-organized talk. A handful of relevant papers are provided on the topic list; use these as a starting point and guide, but follow references within as necessary and read additional material. Try to choose a topic that might become a basis for your course project, so that this background reading can serve as a literature review.

The presentation should be approximately 45 minutes and include these components:

- clear statement of the problem (and scope of background reading)

- why the topic is interesting

- why the problem is difficult

- common assumptions applied

- key technical ideas, strengths and weaknesses

- means of evaluation: how are methods in this area tested?

- what appears to work well today

- open problems and issues raised in the literature

- specify potential points of discussion for the class

The key point is to synthesize the material and describe how the technical contributions fit together when possible. Since the reading is paper driven, it can be tempting to make a presentation that catalogs them one by one. Please resist that temptation. Aim to highlight the coolest things you encounter or learn in the reading, and point out the missing pieces and limitations of the state-of-the-art. Try to criticize and suggest alternatives to the approaches in the papers.

Use applications to motivate the work, and look for visual elements to put in the presentation. Check out the webpages linked on the topic list, and also look at authors’ webpages for supplementary materials. It’s ok to grab a few slides from conference talks etc., but the message and organization of the presentation should be in your own voice. Keep in mind that the entire class will have read only a portion of the papers read and covered by the presenter.

Timetable:

· By the Wednesday the week before your presentation is scheduled: email slides to the instructor, schedule time to meet and discuss.

· The week of your presentation: refine slides, practice presentation, know about how long each part requires.

· The day of your presentation: bring hardcopies of slides for class members, send final slides as PDF file to instructor.

Demos

For each topic one person will present a “demo” of some main idea in a paper we read. When you are in charge of the demo, basically your job is to implement a distilled version of an essential technical idea in the paper, and show us some toy example of how this works in practice. For a number of papers, you may be able to find code or binaries provided by the authors online. The goal is to help us gain a more complete intuition about the work we are studying.

You might:

· experiment with different types of training/testing data sets

· examine the method’s sensitivity to relevant parameter settings

· show a simplified example that highlights an expected strength/weakness of the approach

Note that the goal here is not to recreate published results or to build systems as described in the paper. Instead, you are looking to make a small illustrative demo that will let us more deeply understand what we have read. Spend some time playing with your implementation, and put thought into what would be an instructive toy example to show the class. The demo should allow us to learn something about the method, not just see it. If you needed to implement something yourself, explain how you did it, and especially point out any details or choices that weren’t straightforward.

A demo presentation should take about 20-30 minutes. Be sure to explain the rationale for the outcomes, and conclude with a summary of the message(s) your example illustrates.

Timetable:

· By the Wednesday the week before your presentation is scheduled: email slides to the instructor, schedule time to meet and discuss.

· The week of your presentation: refine slides, practice presentation, know about how long each part requires.

· The day of your presentation: bring hardcopies of slides for class members, send final slides as PDF file to instructor.

Projects

As part of this course, students will complete research-oriented projects in pairs. A project could be built around any of the following:

· an extension to one of the techniques studied in class

· an in-depth analysis and empirical evaluation of one or two related techniques

· design of a novel approach and accompanying experiments

Initial project proposals will be due before the middle of the term. Proposal guidelines are here. We will do a peer review of the project proposals and drafts of the project papers.