Fall 2018 CS498 Four-Credit Projects

Proposals due October 11, progress reports November 16, final reports due end of semester (date TBA)


Jean-Simeon Chardin, House of Cards, 1736

If you are enrolled in the course for four credits, you are required to complete a project for 25% of your grade. Projects can be done in groups of up to three people. Project formats include, but are not limited to, the following:
  • Implementation or demo: Find a research paper related to the topics covered in class and implement their method. Apply existing methods to new datasets. Compare and contrast several methods, adapt or modify them. If feasible, create a demo that can be shown in class.
  • Kaggle competition: Find a competition on Kaggle and implement a deep learning system to enter in it.
  • Paper: Write a survey or tutorial paper on the topic of your lecture (or a different topic if you insist). Models for this kind of paper include Carl Doersch's tutorial on variational autoencoders and Ian Goodfellow's tutorial on generative adversarial networks. If the topic you have chosen already has a good recent tutorial like the two above, this would probably not be the best choice (unless you feel you can write a significantly different tutorial that can offer independent value). The paper should be at least 10 pages in length (single-spaced, single column, 11pt font, 1 inch margins) and typeset in LaTeX.
  • Video: Create a compelling MOOC-style short video (or several videos) on some concept related to the class -- you can see here for inspiration. If you choose to go this route, the bar for production values is reasonably high.
Project deliverables (submissions on Compass):
  • Proposal (due Thursday, October 11th): Proposal should be uploaded to Compass in PDF format by one group member and should include: (1) names of group members; (2) a description of the proposed project in a half a page or so; (3) key references, including links to any resources you plan to use (especially code and data). You will receive feedback on your proposal but not a formal grade. However, failure to turn in the proposal on time will result in a penalty on the overall project grade.

  • Progress update (due Friday, November 16th): A summary of your current efforts, with notes on any modifications to your original project goals. If you are writing a tutorial or survey paper, you should provide a rough draft with a comprehensive list of references. If you are doing an implementation project, at the very least, you should show evidence of successfully running baseline code (e.g., training an off-the-shelf model) on your target data. The target length is three pages. As with the proposal, you will receive feedback, but not a formal grade, and failure to turn in the update on time will result in a penalty on the overall project grade.

  • Final deliverable (due at the end of semester): Either an implementation report with results, the completed paper, or the video(s). You will likely have an opportunity to do a short presentation or demo on the last day of class for extra credit.
Format for implmentation report: The final report should be submitted in PDF format by one designated group member on Compass. It should be (the equivalent of) at least six pages (single-spaced, 11 point font, 1 inch margins) and mimic the style of a research paper. Here is the outline to follow for the report:
  1. Cover page: executive summary: List title and authors. Briefly summarize your problem, line of attack, and most interesting/surprising findings. Be sure to include at least one diagram or example result figure. This is not counted in the six-page minimum.
  2. Introduction: Define and motivate the problem, discuss background material or related work, and briefly summarize your approach.
  3. Details of the approach: Include any formulas, pseudocode, diagrams -- anything that is necessary to clearly explain your system and what you have done. If possible, illustrate the intermediate stages of your approach with results images.
  4. Results: Clearly describe your experimental protocols and identify any external code and datasets used. Present your quantitative evalution (if any) and show some example outputs. If you are working with videos, put example output on YouTube or some other external repository and include links in your report.
  5. Discussion and conclusions: Summarize the main insights drawn from your analysis and experiments. You can get a good project grade with mostly negative results, as long as you show evidence of extensive exploration, thoughtfully analyze the causes of your negative results, and discuss potential solutions.
  6. Statement of individual contribution: Required if there is more than one group member.
  7. References: including URLs for any external code or data used.

Grading

You have to submit your source code (if any) for documentation, but grading will be be based primarily on the quality of the report (strength of idea, clarity, thoroughness, extent of analysis, etc.). More will be expected of larger groups. You can still get a good grade if your ideas do not work out, as long as your report shows evidence of extensive analysis and exploration, and provides thoughtful explanations of the observed outcomes.