Skip to content

alexjungaalto/FederatedLearning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Welcome to CS-E4740 - Federated Learning

This master-level course is offered in Spring 2025 at Aalto University

Enrollment Options:

  • Finnish University (or University of Applied Sciences) Students
    Please contact your study administrator for enrollment details.

  • Open Access
    Anyone interested in following the course without formal enrollment can subscribe to the course mailing list.


Course Content


Abstract

Federated Learning (FL) is a decentralized approach to training machine learning models, designed to retain local data privacy by training models without centralizing datasets. This course covers the fundamental linear algebra and calculus needed to analyze and design FL systems, focusing on real-world applications like weather forecasting and healthcare.

Participants will learn:

  • to formulate FL applications as optimization problems
  • to design FL algorithms using distributed optimization
  • about key requirements for trustworthy AI
  • to critically evaluate the trustworthiness of FL systems

An optional student project offers an extension to 10 credits. The projects allows you to pilot research ideas and obtaining peer feedback.


References

  • A. Jung, "Machine Learning: The Basics," Springer, Singapore, 2022. Available via Aalto Library: here. Preprint.
  • A. Jung, "Lecture Notes for CS-E4740 Federated Learning," Aalto University, 2024. click me

Copyright and License

This material is provided for educational and research purposes. Free use and redistribution are permitted with appropriate attribution. Please credit CS-E4740 - Federated Learning, Aalto University in any shared or derived works.

Preferred Citation:
A. Jung, "Lecture Notes for CS-E4740 Federated Learning," Aalto University, 2024.