Federated Learning Workbench

The case is simple: 10 people each know how to write a number. They all want to develop an algorithm that can recognize handwritten letters, but no one wants to share their number. Federated learning and a private sum protocol to the rescue. This page demonstrates a demo protocol that can do just this. The protocol has 2 main pieces:

This investigation into federated learning is based on the tfjs MNIST example.

For more information see the about page.