Wisdom of the machines : federated learning using OPAL

Abstract

Wisdom of the crowds (WOC) is an old concept that started by recording and aggregating people's estimations. It is one of the useful tools that exists today and allows many estimation applications to work correctly. Moreover, Open algorithms (OPAL) is a useful platform that enables institutions and individuals to share sensitive data, and increases the privacy of the data. In addition, federated learning is a new way to build and generate machine learning models by aggregating their hyperparameters. In this thesis, I show how to combine the three different concepts to build machine learning models on top of OPAL that utilize federated learning on a network. I then extend OPAL to support this new feature and demonstrate how to build a machine learning model using small independent models.