CSCE 478/878 Project Rules

1. Before you begin your project, you are to submit to me, in text format in the body of an email, a 2–3 paragraph proposal of your project. This is due by Sunday, October 9 at 11:59 pm. You should outline the scope of your project (i.e. what the problem is), what you plan to do for your project, and a few ideas of sources (beyond just using the textbook). I will respond soon after with my assessment of your project (i.e., whether or not you may do it) and some suggestions on the scope and possible sources.
2. Projects are due by 11:59 pm on Wednesday, December 7. Wednesday, December 14.
3. By the project deadline you are to submit, via handin:
   • A project writeup (in a separate pdf file) of approximately 10–15 pages (more on this below)
   • In a zip file:
   • On-line copies of the papers you cite in your report, in .pdf format.
   • All source code and data (in text format)
4. Your writeup should include the following sections (some may be very short or nonexistent, depending on the scope of your project).
   • Problem definition
   • Related work
   • Your approach(es)
   • Experimental results
   • Conclusions and ideas for future work
   • References
5. If your project is an implementation, you need something for each of the above items. For those doing an overview, the "Your approach(es)" section will be replaced by an expanded "Related work" section, where you go into more detail on some of the approaches you are reviewing. Also, your "Experimental results" section will summarize the experimental results of some of the papers you review.
6. A note on "Related work": Your project must include a bibliography of at least 2–4 papers, and a brief discussion (one page is plenty) of their content and relevance to your project. EVERY project is expected to have a section of this kind, even if it is an implementation. (You can review how others have attacked this problem [including citations] and give a brief review [and citations] on the approach(es) you're considering.) If you do not know of related papers yet, then you might try browsing relevant sections of the text, and/or look through recent conference proceedings such as the International Conference on Machine Learning, and recent journal articles in the journals Machine Learning and Journal of Machine Learning Research. You may also cite the textbook if it gives a good overview of something relevant to your project, but you can do just as well by reading the papers the book cites.
7. You should also look at Tips on Presenting Technical Material since you will be heavily graded on oral and written presentation of your results.

Last modified 01 December 2016; please report problems to sscott AT cse.