For details about the evaluation criteria for the project, as well as the logistics, please see the course outline in D2L. Here we provide some supplementary materials, some sample topics for projects, and an FAQ which will be expanded throughout the semester as we receive student questions.

Project Proposal and Final Report Template

We will be using the IEEE Conference template in a double column format for the project proposal and final report. The font size should be 10 or 11. The page limit for the proposal is 2 pages including all pictures, tables, and references. The page limit for the final report is 6 pages, where the 6th page can only have references. The use of Latex for writing up these documents is recommended but optional.

Project Ideas

You are expected to find a project that interests your group with the help of the TAs and your instructor. Since the project is the majority of your grade, you are expected to find a project that is "significant". To have an idea what this means, please see the Stanford Machine Learning course projects from previous years 2017, and 2018.

The following sources can give you ideas for projects:

  • University of California, Irvine data set repository: has many public data sets that can be used for your project.
  • Kaggle: has a large number of data sets as well as competitions. If you choose to compete in one of the competitions as part of your project, and manage to finish in the top 3, you might also win some cash prizes from kaggle besides an A+ in the course!
  • Data For Good: is a collective of do gooders, who want to use their powers for good, and not evil, to help make our communities better through data. They typically have limited number of projects, but you can contact them to see if they have a project that interests you.
  • Search the Internet! There are many examples or machine learning projects in finance, computer vision, natural language processing, healthcare, robotics, and more. For example, Denis Shiryaev does practical work on style transfer, image reconstruction, and denoising. As one example here is a upscaled and colorized video from 1906 San Francisco. There are some old videos of Toronto that are waiting to be upscaled and colorized.


Will be populated soon.