- Fri., Apr 7: Project Proposals
- Mon., May 8: Project Milestone
- Thu., June 1, 9-11:30am: Poster Session
- Weds., June 7: Project Report
Your Course Project
Your class project is an opportunity for you to explore an interesting machine learning problem in the context of a real-world data set. You are also free to explore theoretical and algorithmic ideas, and you must have a data component. It is important that your project be scientific in nature: you should ask a well motivated question and provide some quantitative way to judge the outcomes. This need not preclude creative projects.
Feel free to look at previous years, other courses, kaggle, etc for seed projects. Post to the discussion board to ask questions and to share your ideas. You have to make sure you have the data is readily available, since a quarter is too short to explore a brand new concept.
Projects can be done by you as an individual, or in teams of two students. You can discuss your ideas and approach with the instructor/TAs. The final responsibility to define and execute an interesting piece of work is yours.
The grading of the final project is split amongst three deliverables:
- A project milestone (20% of the grade).
- A project poster presentation (20% of the grade).
- A final report (60% of the grade).
Your final report will be evaluated by the following criteria:
- Scientific merit: Did you explore your question with sound reasoning? Can you draw quantitative conclusions from you work? Are you taking a justifiably simple approach or, if you are choosing a more complicated method, do you have sound reasoning for doing this? If your project is on the creative axis, then you must still find a way to quantitatively judge your outcomes.
- Technical depth: How technically challenging was what you did? Did you use a package or write your own code? It is fine if you use a package, though this means other aspects of your project must be more ambitious. How challenging was dealing with the data set that you used? How challenging was your project in scope? How detailed was it?
- Presentation: How well did you explain what you did, your results, and interpret the outcomes? Did you use good graphs and visualizations? How clear was the writing? Did you justify your approach? Did you present related ideas and related work clearly?
Project proposal format: Proposals should be one page maximum. Include the following headings:
-
Project title
-
Data set. Provided a link to the dataset and a clear/concise description. If the dataset is not for distribution, state this and why.
-
Project idea. This should be approximately two paragraphs.
-
Relation to your research. YOUR PROJECT MUST CONTAIN NEW WORK. If your project is related to your research, you must state what will be novel. If it is not, you should write "This project is not a continuation of my current research."
-
Software you will need to write and software you plan to use.
-
Papers to read. Include at last 3 relevant papers. If you are doing something different then one of the suggested projects, you will probably want to read at least one of them before submitting your proposal.
-
Teammate: will you have a teammate? If so, whom? Maximum team size is two students. One proposal per team.
-
Milestone: What will you complete by the milestone? Experimental results of some kind are required.
A project milestone should be submitted on Canvas. Your write up should be 3 pages maximum in NIPS format, not including references. You must use the NIPS LaTex format. You should describe:
- summary of related work in the literature (with references).
- the results of your first experiments here.
- the reasoning for your approach. Here, comment on appropriate baselines for comparison, and what would be related approaches.
We will hold a poster session in the Atrium of the Paul Allen Center. Each team will be given a stand to present a poster summarizing the project motivation, methodology, and results. The poster session will give you a chance to show off the hard work you put into your project, and to learn about the projects of your peers.
Here are some details on the poster format:
- We will provide poster boards that are 32x40.
- Both one large poster (recommended) and several pinned pages are OK. The TAs can help with printing your posters, provided you give them enough notice.
You must submit your poster on Canvas.
Your final submission will be a project report on Canvas. Your write up should be 8 pages maximum in NIPS format, not including references. You must use the NIPS LaTex format. You should describe the task you solved, your approach, the algorithms, the results, and the conclusions of your analysis. Note that, as with any conference, the page limits are strict. Papers over the limit will not be considered.
Feel free to look at previous years, other courses, kaggle, etc for seed projects. Post to the discussion board to ask questions and to share your ideas. You have to make sure you have the data is readily available, since a quarter is too short to explore a brand new concept.