Fairness and Privacy in Machine Learning
This course gives a thorough technical introduction to algorithmic privacy and fairness. The course work is centered around individual assignments and group project work.
- Introduction: algorithmic privacy, fairness and reproducibility.
- Privacy and anonymity
- Differential privacy
- Approximate differential privacy
- Privacy amplification
- Group fairness: Equalised odds
- Group fairness: Balance and calibration
- Individual fairness: Meritocracy
- Individual fairness: Smoothness
- Reproducibility
Details
Code |
62116 |
Type |
Course |
ECTS |
5 |
Site |
Neuchâtel |
Track(s) |
T6 – Data Science
|
Semester |
A2022 |
Teaching
Schedules and Rooms
Period |
Weekly |
Schedule |
Tuesday, 08:15 - 12:00 |
Location |
UniNE, Unimail |
Room |
B013 |
Evaluation
Evaluation type |
written exam |
Additional information
Comment |
First Lecture
The first lecture will take place on Tuesday, 27.09.2022 at 08:50 in UniNE, Unimail, room B013.
|