Project Guidelines

If you are taking CSE 252C for four units of credit, you must either take the final exam or do a project in addition to completing all of the homework assignments. The project should be at the frontier of current research, but need not necessarily move the frontier forward. Replicating the results of an innovative recent paper would be a good project, for example. Projects must be closely inspired by one or two specific recent high quality papers. They should preferably have an experimental component, but "crass empiricism" is to be avoided. As much as possible, you should use a high-level programming environment such as Matlab. The schedule for the projects is as follows. After each deadline, the instructor will be available to discuss the projects in person. You should take the initiative to set up an appointment, preferably on a Wednesday or Thursday.

If you are having trouble thinking of a project idea, you can use this list of suggested projects as a starting point.

(1) On Monday April 23 at 6pm or earlier, you should hand in a project proposal. This should explain explicitly and clearly what you will do. In particular, the proposal should include:

• a list of four to six milestones, and deadlines to achieve the milestones

• a list of questions to be answered during the project and discussed in the report

• if the project is experimental, which existing software you will use directly or build upon

• if the project is experimental, precisely which datasets you will use and where you can obtain them quickly

• a few recent and very closely related papers that you will build on, with full bibliographic data.

The proposal should be written in well-organized continuous English, as opposed to just an outline. Most of its text should be reusable in your final report. In organization, proposals may resemble the project descriptions for CSE 250A, 250B, or 254.

(2) On Monday April 30 at 6pm or earlier, please hand in a revised project proposal. This must follow all the instructions above, and take into account comments received from the instructor and other sources. It should be two to four pages long when formatted following the NIPS format or one to two pages long using the CVPR format. Since you will have to use LaTeX eventually, you should start now with the revised proposal. In the first phase of the project, some important tasks include:

• formulating clear, sensible hypotheses to test,

• finding useful training sets and test sets,

• surveying closely related recent papers, and

• selecting and obtaining existing software, and developing new software.

These are tasks that can and should be performed mostly in parallel, not sequentially.

(3) On Wednesday May 23 at 6pm or earlier, you should hand in a complete, polished draft of your project report. The report should resemble as closely as possible a good submission for a computer vision or pattern recognition conference. You should follow either the NIPS or the CVPR formatting instructions and the 250A report guidelines.

(4) On Wednesday May 30 at 2pm or earlier, you should submit the final version of your project report in both hardcopy and pdf format (by e-mail). This will be graded following the 250A grading criteria. Perfect academic honesty is required. The final version of your report should be a PDF file in NIPS or CVPR format that is under one megabyte. Avoid these common formatting mistakes. To maximize the readability of your paper, and to minimize the size of the PDF file, make sure that you use only standard Postscript fonts. Use the command \usepackage{pslatex} in LaTeX to achieve this. Also provide an ascii abstract of your report that follows these guidelines and is 150 to 200 words long.

While doing the project, remember that winning at research is similar to winning in many other fields of endeavor.

Content adapted from Charles Elkan's CSE 254 Project Guidelines.