Short Description:
Privacy-preserving federated learning is an emerging machine learning paradigm that aims to learning
knowledge from data distributed on different places without requiring to transmitting the data to a
central server. This way, the privacy of the data can be preserved. This project aims to develop a
federated, communication efficient, secure federated learning framework that can training deep
learning models with distributed data.
Required skills (e.g. mandatory courses, if required)
• Basic knowledge of machine learning
• Hands-on Python programming skills
In case this would not find enough interest for a team project, this project proposal would be also
offered (in reduced/modified form)
• an individual project
• a project for only 2 students
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-GP Grundlagenprojekt Intelligente Systeme | weiteres Projekt | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.