CMPT 880: Final Project

The intent of the course project is to give you some further experience with deep learning, especially hands-on. I am open to your own projects and ideas, as long as you they are related to deep learning in a meaningful way. A good chance for getting feedback is the project outline presentation. In addition, feel free to visit me during my office hour or talk after class.

Methodology

The key components, and those on which you will be graded, are:

• Choosing the right problem. Ideally you will have a problem from your current/potential research area which could benefit from the use of deep learning techniques. Please feel free to use this problem for your project. However, you must not submit work you have done before this course as your project.

  If you haven't decided on a research area of your own, or would like to work on something different, that is fine too. A great resource for datasets to work on is the UCI repository.

  Don't choose something that is too hard nor too simple. If in doubt, please come to my office hours and ask about your topic. A rough guideline for grad projects is that they should be approximately 2 times as much work as an assignment in a grad course.

• What has been done before? A month in the lab can save you a day in the library. This is a course project, and not a peer-reviewed paper, but you should be aware of the most closely related work. I expect roughly 3-5 references to other work.

  You must also maintain high standards of academic integrity. Standing on the shoulders of giants is highly recommended, just make it clear who these giants are. If you use someone else's code, you must provide a referenece. If you use text/equations from someone else's paper, you must cite and quote it. If you use figures from another paper, you must clearly state such.

• Comparative experiments. You must compare what you have done to at least one other method to know if anything interesting has been achieved. Proper experiments should only change one component at a time (e.g. different classifier, same features). You should also study different parameters of algorithms to ascertain sensitivity (e.g. regularization parameter values). If you are using a standard dataset, you can compare your results (one method) to others'. Just make sure the experiments are comparable (e.g. same training/test data).

  You will not be graded on the quality of your results, but on the quality of your experimental methodology. A negative result is fine, e.g., "deep belief nets don't work on this problem".

• Quality of exposition. Clearly state the problem you worked on, the methods you used, who has done what before, what was the intent of your project, which datasets, and what parameters you used. Create figures with legible fonts and labelled axes, and provide figures visualizing your results.

  A standard project presentation has four parts:

  1. Introduction (includes discussion of closely related work)
  2. Approach
  3. Experiments
  4. Conclusion

Grading Criteria for Final Project.

• 30% Presentation. Clarity, conciseness---quality of exposition.
• 40% Originality. To what extent were you creative in developing your own ideas?
• 30% Evaluation, methodology.