Passing Examples :
-
Eye-to-Eye : The most well-formed project proposal. This group has already moved past the submission stage and has started fleshing out the final project body. The original proposal contained a very clear problem description, a very clear model (incorrect but present), and a path for getting to the solution. Latent variables were identified, etc.
-
Map-Via-HMM : This was probably the weakest of the passing proposals. It should have had a more mathematical description of the problem, however, given the problem setup it was clear what the problem was, what the latent variables were, how the data would be obtained, and what the inference challenges would be.
-
Tissue-Classification : This was right in the middle. Safe, well-crafted, clear problem. Where are the boundaries of a particular tissue type? Not mathematically precise enough either, but, that’s what we’re learning about isn’t it?
Final Project Instructions
The final project is meant to be a semester-long, significant piece of work that demonstrates your data mining / statistical machine learning knowledge on a problem domain of interest to you (and hopefully also of interest to a larger academic, governmental, or industry community). The deliverables include a (2 (preferred) - 3 (max) page proposal (single space, 11pt font, single column – required formatting instructions below)); (possibly) a 3-5 minute proposal presentation; a short, publication-quality paper (4 (preferred) - 6 (max) pages, same format); and a 10-20 minute presentation. You will fail to complete a satisfactory final project if you wait until the last minute to begin the project.
Schedule :
-
[1/19/2012] : Initial project groups are to be formed by this date. A project team may consist of 4 people maximum. Groups consisting of 2-3 people are preferred. Single member groups are discouraged but OK. Groups should submit (in class) a single page with group member UNI’s and a working title for the project.
-
[1/26/2012] : Proposal due (printed, in class).
The proposal will be graded and will count as 20% of the final project grade. The proposal should take the form of a research abstract, i.e. it should include a title, authors, abstract, introduction, problem description, data source, expected conclusions, and references. Note that the only significant missing pieces should be the methods and results. All sections will grow in the final project report, but those listed should appear in the project proposal in reasonably complete form. Of particular interest are a description of the problem to be solved, the data to be used, a detailed description of how it is to be (or was) collected, a literature search of analyses already performed on the data and the conclusions drawn from those analyses. Project proposals that do not outline a project with sufficiently high complexity will be given zero credit and groups that author such proposals will be required to resubmit project proposals on a weekly basis thereafter until the proposal reaches a sufficient level of complexity to warrant a passing grade. Resubmissions will receive strictly lower grades than proposals that pass the first time.
-
[later (possibly)] Short in-class presentation of proposal (2-3 slides).
The proposal presentation should clearly introduce the team members, the project topic, and the data to be used. Ideas about what inference tools might be employed will ideally be included as well.
-
[Final Exam Period] : Final papers due and final project presentations are to be given at this time. The presentation will be graded and will count as 10% of the final project grade. Each group will present their results in a short in-class presentation (single presenters are preferred). The duration of each presentation will depend on the total number of groups formed, but almost certainly will not exceed 10 minutes. Slides for the presentations (plan on 1-2 per minute of presentation) must be delivered electronically to the instructor via the class email by 12:00am, midnight, the day of the final exam period. Failure to submit .pdf slides by then will result in a grade of 0 for the final project. The presentation should introduce the problem, highlight the methods used, and cover analysis results. Each group will be subject to 5-10 minutes of questioning from the instructor, the TA, potentially guest reviewers, and the other students in the class about all aspects of their project. Having backup slides (slides prepared, but not used in the presentation) for questions about methodology detail will be expected of all groups.
Paper formatting materials
Latex (yes!) is required for proposals and papers. Included here are a number of files that should be used to prepare a properly formatted paper.
Instructions for use : download all of the files to a single folder then run “pdflatex main; bibtex main; pdflatex main; pdflatex main.” This will produce a file “main.pdf.” Edit main.tex to include elements related to your final project. Google extensively to learn latex. Math symbols are particularly easy to look up.