Abstract: 

Federated Learning is an emerging paradigm that enables one to perform machine learning without centralizing training data in a single place, allowing local clients to collaboratively train a shared global model.
Federated learning offers a solution for consortia, multi-national enterprises, and networks of edge devices to benefit from training across individual datasets while respecting data privacy concerns, and accommodating network bandwidth limitations and limited device availability.


In this workshop you will learn when and why federated learning should be used, basic algorithms for implementing it, as well as more advanced ones covering a variety of use-cases. Towards the end of the workshop participants will be offered a hands-on experience of training a federated model together.

Bio: 

Dr. Laura Wynter is the head of the RealWorld AI team at the IBM Research Singapore Lab. Laura has degrees from MIT and the Ecole des Ponts (Paris, France). Her areas of expertise involve the use of AI as well as optmization, equilibrium modeling and statistics-based methods for enabling effective real-time decision making for planning and operational problems in numerous domains. She has been named an IBM Master Inventor. Her work spans the full lifecycle of a research solution from the definition of the research problem and its characterization, to the development of effective algorithms, to collaborations with the IBM software division culminating in the creation of commercial software products from the models and algorithms developed.