Projects
Credits: Much of the architecture for this course project comes from Bryan Low (NUS) and Thorsten Joachims (Cornell)
Warning ⚠️: this section of the website is still undergoing revision for this semester. Last updated 8 Jan 2022, to sync with current weightage. ⚠️
A key part of the mastery of any skill is practicing it, outside of the formal algorithmic basis for the topics. The student projects form an integral part of the assessment. Student groups should have 4 to 5 group members and will be partially self-assembled (into groups of size 1 to 3) and then assembled by the teaching staff into final groups with project preferences and expertise taken into account. You will also be assigned a contact TA as project mentor that you should use as a resource for questions and advice. The TA will correspond with you and attempt to check in with you on a weekly basis. It is your responsibility to ensure that your group meets with your project mentor, not your mentor’s responsibility to chase you.
Due to the high demand for this course, we have had to make concessions in the scope and variability of the our project component. The staff will propose a set of suitable datasets for students groups to work with.
Note that performance on the different macroscopic metrics is not the critical factor in your grade on the project. We primarily evaluate with respect to the (interesting) ideas your team employs to solve the task.
Project Structure
| Description | Percentage |
|---|---|
| Intermediate Project Update | 5% |
| Final Project Report | 30% |
| Total | 35% |
The staff (project mentor and instructor both) will give you feedback on your group’s Intermediate Update.
In Weeks 10–12, your group may decide to meet with an instructor for additional, ungraded consultation session to offer final advice. Your team will need to prepare a short presentation deck to present to the staff about the progress of your project.
Detailed grading rubrics for all phases of the project are provided as part of the project reporting templates provided in class.
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 group)
- Significance (are the questions you are asking interesting)
Detailed grading rubrics will be made available over the course of the project.