Federated Learning: A Primer for Mathematicians by Mei Kobayashi(.PDF)

File Size: 11.8 MB

Federated Learning: A Primer for Mathematicians by Mei Kobayashi
Requirements: .ePUB, .PDF reader, 11.8 MB
Overview: This book serves as a primer on a secure computing framework known as Federated Learning (FL). Federated Learning is the study of methods to enable multiple parties to collaboratively train Machine Learning/AI models, while each party retains its own, raw data on-premise, never sharing it with others. This book is designed to be accessible to anyone with a background in undergraduate applied mathematics. It covers the basics of topics from Computer Science that are needed to understand examples of simple federated computing frameworks. It is my hope that by learning basic concepts and technical jargon from Computer Science, readers will be able to start collaborative work with researchers interested in secure computing. The purpose of this monograph is to introduce Federated Learning, a framework that enables multiple parties to securely share local AI models—not the raw data, itself—to build a high-quality global AI model. This monograph assumes that readers have an undergraduate mathematics background, i.e., basic knowledge of calculus, basic linear algebra, and elementary statistical concepts.
Genre: Non-Fiction > Tech & Devices

Free Download links:

https://trbt.cc/xytoujq30v9p.html

https://katfile.com/lpns7u80b89t/Federated_Learning_A_Primer.rar.html