Seminar

Abstract: 

Federated Learning as a decentralized machine learning solution can solve a variety of problems in real world applications. It enables a continuously self-improving AI, which can be deployed at the edge for training on private and decentralized data. However, Federated Learning requires expertise from multiple domains and adaption to the specific usecase. In our overview talk we will present various aspects of Federated Learning like architectural patterns, algorithms or privacy.