You're reading from Federated Learning with Python Design and implement a federated learning system and develop applications using existing frameworks

Product type Paperback

Published in Oct 2022

Publisher Packt

ISBN-13 9781803247106

Length 326 pages

Edition 1st Edition

Languages

Python

Tools

Federated Learning

Concepts

Design

Authors (2):

George Jeno

Kiyoshi Nakayama, PhD

View More author details

Table of Contents (17) Chapters

Preface

1. Part 1 Federated Learning – Conceptual Foundations

2. Chapter 1: Challenges in Big Data and Traditional AI FREE CHAPTER

3. Chapter 2: What Is Federated Learning?

4. Chapter 3: Workings of the Federated Learning System

5. Part 2 The Design and Implementation of the Federated Learning System

6. Chapter 4: Federated Learning Server Implementation with Python

7. Chapter 5: Federated Learning Client-Side Implementation

8. Chapter 6: Running the Federated Learning System and Analyzing the Results

9. Chapter 7: Model Aggregation

10. Part 3 Moving Toward the Production of Federated Learning Applications

11. Chapter 8: Introducing Existing Federated Learning Frameworks

12. Chapter 9: Case Studies with Key Use Cases of Federated Learning Applications

13. Chapter 10: Future Trends and Developments

14. Index

Why subscribe?

15. Other Books You May Enjoy

Appendix: Exploring Internal Libraries

Technical requirements

The Python algorithm implementations presented in the book can all be found in the ch7 folder, which is located at https://github.com/PacktPublishing/Federated-Learning-with-Python/tree/main/ch7.

Important note

You can use the code files for personal or educational purposes. Please note that we will not support deployments for commercial use and will not be responsible for any errors, issues, or damages caused by using the code.

For the pure aggregation algorithms, auxiliary code is included to display example output from preset local parameters. The aggregation methods that modify the local training process require an FL system in order to operate – for these, full implementations using STADLE are included. Also, the pure aggregation algorithms can be directly tested with STADLE by configuring the aggregation method. Information on how to run the examples can be found in the associated README files.

The installation of the stadle-client package...

The rest of the chapter is locked

You're reading from Federated Learning with Python Design and implement a federated learning system and develop applications using existing frameworks

Table of Contents (17) Chapters

Technical requirements

Unlock this book and the full library FREE for 7 days

Authors (2)

Personalised recommendations for you