Final Project Presentations
The presentations should be no more than 10 slides per team.
Each team (19 total) will present for 8 minutes in class.
All team members are expected to be present, but a subset may present.
During your presentation, please cover the following:
A) Introduction
Problem statement: What problem does this project solve? (Or what question does it answer?)
Motivation: Why is this an important or hard problem?
Background: What related or previous work is relevant to the project?
Tiny Sell: What will your work in this project add to the Background in order to address the Problem Statement?
B) Research
Data: What data does this project use to address the Problem outlined above?
Sourcing/Labeling: How was this data collected/labeled, and what considerations does that bring to your project?
Approach: How will you approach the problem with Machine Learning methods/tools/systems?
Methods/Experiments: What methods and experiments did you settle on?
C) Results
What are the new contributions of this paper? / What did you achieve?
What are next steps?
What are limitations?
D) Team Contributions
What were the respective contributions of the team members?
Final Project Report
Please use the ACM single column template if you have no target venue. If you have a target venue, please use the appropriate template for future ease. Examples of papers from NeurIPS, FacCT and SERC are good to follow.
The page length should be dictated by the target venue which in general will be 8–10 pages, but can be longer.
Remember that the sections for the report should be as follows:
A) Introduction
Problem statement: What problem does this paper solve? (Or what question does it answer?)
Motivation: Why is this an important or hard problem?
Background: What related or previous work is relevant to the project?
Tiny Sell: What will your work in this project add to the Background in order to address the Problem Statement?
B) Research
Data: What data does this project use to address the Problem outlined above?
Sourcing/Labeling: How was this data collected/labeled, and what considerations does that bring to your project?
Approach: How will you approach the problem with Machine Learning methods/tools/systems?
Methods/Experiments: What methods and experiments did you settle on?
C) Results
What are the new contributions of this paper? / What did you achieve?
What are next steps?
What are limitations?
D) References
