Grades

Classes will consist of a combination of lectures and student-led discussions of papers. Student responsibilities include paper critiques, one paper presentation, homeworks, and a class project. The semester grade will be determined based on performance in this areas.

1. Paper Critiques. For each (non-optional) paper assigned in class, prepare a critique of the paper and mail the critique to cs6362-turnin@cse by 5:00 p.m. on the day the paper will be discussed. Each critique should be no more than one page in length and will be graded on a scale of 1 to 5. The grade will be based on 1) accurate summary of the paper, 2) insightful analysis of the strengths and weaknesses of the technique and comparison to other approaches, 4) suggestions for improving or extending the technique described in the paper, and 5) statements indicating how this particular technique will impact the future of high-performance AI.
2. Paper Presentation. Throughout the semester, each student will have an opportunity to lead the discussion in class on the assigned paper. This discussion will be graded on a scale of 1 to 50, based on the following criteria: 1) accurate and clear summary of the paper, 2) ability to field questions on the approach, 3) comparison of the paper to related material, 4) ability to lead discussion analyzing strengths and weaknesses of the approach, and 5) integration of extra material including related optional papers, detailed examples of the techniques, suggestions for improvements, etc.
3. Class Project.

   The project requires a novel idea, design and implementation. A one-page project proposal is due in class on March 13. The project is due on the last day of class, along with a writeup (less than 15 pages) describing your system and the results.