Introduction to Federated Learning: Fundamentals and Applications. 3 credits

Catalog description

This course aims to provide students with a thorough understanding of Federated Learning (FL) principles, algorithms, and applications, particularly in the IoT domain. It will highlight the differences between centralized and decentralized machine learning and foster an understanding of how to enhance the utility, robustness, privacy, and scalability of FL. The skills acquired will enable students to tackle a wider range of machine learning tasks. Students are highly recommended to have completed a course in Machine Learning or possess equivalent practical experience. This course requires proficiency in Python programming for data analysis and training traditional neural networks. Students are encouraged to have prior knowledge of optimization methods such as Stochastic Gradient Descent. Offered by Cyber Security Engineering . Limited to two attempts.