Federated learning is a type of machine learning technique that enables multiple devices or parties to collaborate in training a shared machine learning model, without sharing their data with each other or with a central server. In federated learning, the training data remains on the local devices or servers, and only the updates to the machine learning model are sent to a central server, where they are aggregated to create a new version of the model.
It will provide open source framework/api that will attract federal grants, and potentially will lead to customized software and patentable technology development for commercialisation, startups etc.,
Automated Federated Deep Learning funded Indo-French Centre for the Promotion of Advanced Research (CEFIPRA)