Federated Learning Lecture
Nowadays, Artificial Intelligence, notably Advanced Machine Learning (ML) drives scientific and economic growth worldwide. They are essentially massive ‘learning by experience/examples’ systems. However, as our tasks and the world change, such systems should adapt to new domains/tasks and continue learning. Knowledge should be transferred from one DNN systems to other ones. Distributed DNN training should be performed though Federated Learning, e.g., for privacy protection. New Learning modes should be explored, by reward maximation, as it is done in Deep Reinforcement Learning and Imitation Learning.
This lecture overviews that has many applications in distributed Machine Learning and privacy protection. It covers the following topics in detail: Centralized/Decentralized Learning, Federated Learning principles and platforms, Federated Learning Algorithms (Federated Averaging Algorithm, FedProx algorithm, FedMA algorithm) and Privacy Principles & Technologies, notably: Differential Privacy, Homomorphic Encryption, Zero-knowledge Proof Technologies, Secure Multiparty Computation.