Projects
Credits: Much of the architecture for this course project comes from Bryan Low (NUS) and Thorsten Joachims (Cornell)
A key part of the mastery of machine learning is practicing it, outside of the formal mathematical and statistical basis for the algorithms. The student projects form an integral part of the assessment. Student teams should have 5–6 members and will be assembled by the teaching staff.
Curated Datasets
Not all datasets out there are well calibrated to give beginners a mastery experience in machine learning. We have curated a set of datasets that our staff feel are useful, sufficiently clean and align well with their particular task and type of data to work with. These include datasets for studying time-series, text (natural language), images and videos (vision), as well as datasets exhibiting multiple modalities.
Project Structure
| Description | Percentage |
|---|---|
| Proposal | 5% |
| TA Consultation (Weeks 7–13) | Ungraded |
| Instructor Consultation (Weeks 11–13) | Ungraded |
| Final Project Presentation (Pre-recorded) | 20% |
| Total | 25% |
You will need to form teams and propose a topic to for your project in a formal project proposal. The staff and your peers will give you feedback. After the project proposal, you will be assigned a contact TA that you can use as a resource for questions and advice.
Final Project Presentation
Teams will need to provide the following deliverables:
- A video recording documenting your team’s project, limited to 15 minutes maximum (primary deliverable)
- URL to your team’s project source code (Git repo or Google Colab link)
- Slides used in your video recording (.pptx or .pdf only)
Detailed grading rubrics for all phases of the project will be provided. The general grading metrics are as follows:
- Originality
- Relevance to course
- Quality of arguments (are claims supported, how convincing are the arguments you bring forward)
- Clarity (how clearly are goals and achievements presented)
- Scope/Size (in proportion to size of team)
- Significance (are the questions you are asking interesting)
As with supervised machine learning, sometimes it’s easier to learn from data than from rubrics. You can get a look at past projects by looking the previous iterations of CS3244 projects as housed in SoC’s STePS platform, from either Semester I, AY 21/20’s Project Showcase, Semester I, AY 19/20 or Semester I, AY 18/19.
We also would like to thank Google Workspace for Education for their continued sponsorship of our course by allowing our course administrators to distribute 50 USD worth of Google Compute Engine credits to project teams that have applied for credit for their course project work.