CSE 254 Spring 2002

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
UNIVERSITY OF CALIFORNIA, SAN DIEGO

CSE 254: Seminar on Learning Algorithms

Spring 2002

Update: Project abstracts and reports are here. This seminar will be offered again in Spring 2003.

SCHEDULE OF PRESENTATIONS

The procedure for each student presentation is as follows:

One week in advance: Finish a draft of about 30 slides that present clearly the work in the paper. Make an appointment with the instructor to discuss the draft slides. Email the slides to elkan@cs.ucsd.edu.
Several days in advance: Meet for about one hour to discuss improving the slides, and how to give a good presentation.
Day of presentation: Give a good presentation with confidence, enthusiasm, and clarity.
Less than three days afterwards: Make changes to the slides suggested by the class discussion, and email the slides in PDF, two slides per page, to the instructor for publishing. Try to make your PDF file less than one megabyte.

date	presenter	paper title	author(s)	discussion board	slides
April 2	organizational meeting
April 4	Bianca Zadrozny	Sequential cost-sensitive decision-making with reinforcement learning	E. Pednault, N. Abe, B. Zadrozny and others	here	here
April 9	Kristin Branson	Policy invariance under reward transformations: Theory and application to reward shaping	A. Ng, D. Harada, S. Russell	here	here
April 11	Aldebaro Klautau	On discriminative vs. generative classifiers: A comparison of logistic regression and naive Bayes	A. Ng, M. Jordan	here	here
April 16	Greg Hamerly	Segmentation using eigenvectors: A unifying view	Y. Weiss	here	here
April 18	David Kauchak	Distributed learning of lane-selection strategies for traffic management	D. Moriarty, P. Langley	here	here
April 23	Dana Dahlstrom	Implicit imitation in multi-agent reinforcement learning	B. Price, C. Boutilier	here	here
April 25	Eric Wiewiora	Balancing multiple sources of reward in reinforcement learning	C. Shelton	here	here
April 30	Degui Zhi	Feature selection for high-dimensional genomic microarray data	E. Xing, M. Jordan, R. Karp	here	here
May 2	Sameer Agarwal	Dynamic textures	S. Soatto, G. Doretto, Y. Wu	here	here
May 7	Victor Gidofalvi	Maximum entropy Markov models for information extraction and segmentation	A. Mccallum, D. Freitag, F. Pereira	here	here
May 9	Joe Drish	Conditional random fields: Probabilistic models for segmenting and labeling sequence data	J. Lafferty, A. McCallum, F. Pereira	here	here
May 14	Bret Ehlert	Document clustering using word clusters via the information bottleneck method	N. Slonim, N. Tishby	here	here
May 16	Ben Leong	A natural law of succession (long version)	E. Ristad	here	here
May 28	Yohan Kim	An alternate objective function for Markovian fields	S. Kakade, Y. W. Teh, S. Roweis	here	here
May 30	Eugene Ke	From promoter sequence to expression: A probabilistic framework	E. Segal, Y. Barash, I. Simon, N. Friedman, D. Koller	here	here
June 4	Jim Vaccaro	Learning to use selective attention and short-term memory in sequential tasks	A. McCallum	here	here
June 6	project reports

OVERVIEW

Important note: The room for CSE 254 has changed to APM 4882.

CSE 254 is a graduate seminar devoted to recent research on AI learning methods and applications. This is not an introductory course, so the prerequisite is at least one graduate-level course (at UCSD or elsewhere) in machine learning or a closely related area such as statistics or pattern recognition. Appropriate courses at UCSD include CSE 250B and Cognitive Science 260.

The seminar will meet on Tuesdays and Thursdays from 2:20pm to 3:40pm in ~~Sequoia Hall, room 147~~ APM 4882. The first meeting will be on Tuesday April 2, and the last meeting will be on Thursday June 6, 2001.

Each meeting of 80 minutes will be divided into two parts. First, a student will give a talk lasting about 60 minutes presenting a recent technical paper in detail. In questions during the talk, and in the final 20 minutes, all seminar participants will discuss the paper and the issues raised by it.

Each student will do one term project following specific guidelines. The project should be at the frontier of current research, and preferably closely inspired by at least one of the papers discussed in the class. Project reports will be evaluated using these grading criteria. There is a schedule for handing in a detailed project proposal, a draft project report, and then the final report.

The seminar will have no final exam. Letter grades will be based 20% on the presentations, 10% on participation in class and in the web-based discussions, 10% on intermediate project deliverables, and 60% on the final project report.

The instructor is Charles Elkan, Associate Professor, with office in AP&M room 4856. Feel free to send email to arrange an appointment, or telephone (858) 534-8897.

One textbook is recommended as background reading: Machine Learning by Tom Mitchell, McGraw Hill, 1997, ISBN 0070428077.

REGISTRATION

Students may take the seminar for a letter grade for four units, or for two units S/U:

For two units, a student must present one paper and participate in all class activities.
Four units will require a presentation, participation in all class activities, and a project.

For four units, a student should register for CSE 254, section id 442409, for a letter grade. For two units, a student should register for the instructor's CSE 293, section id 434321.

Students who took the Spring 2001 version of CSE 254 may take it again. All papers will be different this year.

PAPERS AND TOPICS

In the first week, we will make a schedule of papers and presentations for the whole quarter. Papers will be recent technical articles, often from NIPS and ICML. Each paper will be made available on the web as the quarter progresses. Students will choose papers in consultation with the instructor. Relevant topics may include:

supervised learning with many classes
regularization when observed counts are zero or small
discriminative versus generative modeling of data
semi-supervised learning from labeled and unlabeled data
transductive inference
new boosting algorithms
feature selection from very large feature spaces
modeling human heuristics for learning
reinforcement learning algorithms and applications
applications to text categorization
applications to image retrieval
applications in computational biology
financial applications

Some papers will be theoretical, and some will be applied. Each presentation will cover a single conference paper, to ensure that it is explained and discussed in sufficient depth.

PRESENTATIONS

Please read, reflect upon, and follow these presentation guidelines. Presentations will be evaluated, in a friendly way but with high standards, using this feedback form.

Each presentation should be prepared using LaTeX or Powerpoint, and should consist of about 30 slides. You must copy all important equations, diagrams, charts, and tables from the paper into your slides.

For each paper, we will have a web-based discussion area. Each student is expected to contribute at least one message to the discussion, before the presentation. A message may ask an interesting question, point out a strength or weakness of the paper, or answer a question asked by someone else. Messages should be thoughtful!

The schedule of presentations will be determined as much as possible on Tuesday April 2. Students should choose a date first, and then agree with the instructor about a paper to present. To find ideas, students can look at this list of possible papers and contact the instructor.

If you want to change your presentation date, please arrange a swap with another student and notify the instructor at least two weeks in advance.

Most recently updated on July 17, 2002 by Charles Elkan, elkan@cs.ucsd.edu