LinkedIn Facebook twitter home page
New Book AlertsSign Up

Advanced Search

Change Location

 
Artech House UK
Radio Frequency Machine Learning: A Practical Deep Learning Perspective

Radio Frequency Machine Learning: A Practical Deep Learning Perspective

By (author): Scott Kuzdeba
Copyright: 2025
Pages: 310
ISBN: 9781685690335
Coming Soon: Available 02/28/2025

Print Book £114.00 Qty:

Radio Frequency Machine Learning: A Practical Deep Learning Perspective goes beyond general introductions to deep learning, offering a focused exploration of how modern deep learning techniques can be applied directly to radio frequency (RF) challenges. It covers a wide range of applications, including classification tasks where deep learning is used to label and categorize signals based on a labeled training dataset, as well as clustering tasks that group similar signals together without labels. Additionally, it expands into deep learning (generative AI) for waveform synthesis and how reinforcement learning can be used within the domain. This book also investigates advanced topics like RF sensor control, feedback mechanisms, and real-time system operations, offering a comprehensive understanding of how deep learning can be integrated into dynamic RF environments.

 

This resource addresses the practical concerns of deploying machine learning in operational RF systems. It goes beyond applications and techniques, covering how to ensure the robustness of solutions, with insights into data sources, augmentation techniques, and strategies for integrating ML with existing RF infrastructure. The full development process is examined, from data collection to deployment, along with numerous case studies throughout. Looking to the future, the book explores emerging trends like edge computing and federated learning, offering a forward-looking perspective on the continued evolution of RF machine learning.

 

Whether the reader is just beginning the journey into RF machine learning or is looking to refine skills, this book provides an essential resource for understanding the intersection of deep learning and RF technology. This is a must-have resource for anyone interested in the cutting edge of wireless technologies and their potential to shape the future of communication.

Foreword
Preface

 

1. Introduction
1.1 Radio Frequency Machine Learning
1.2 Where to Apply Deep Learning in the RF Domain
1.3 Shifting from Traditional to ML Processing
1.4 Book Organization
1.5 RF ML Ecosystem
1.6 Future Directions
1.7 References

 

2. RF ML Classification
2.1 RF ML: Applications & When to Use
2.2 Data for Classification
2.3. Algorithms & Architecture
2.4. Performance Assessment
2.5. Architecture Studies
2.6. Shifting from Classification to Regression
2.7. References

 

3 RF ML Clustering
3.1 RF ML: Applications & When to Use
3.2 Data for Clustering
3.3 Algorithms & Architecture
3.4 Offline vs. Online Operation
3.5 Performance Assessment
3.6 Architecture Studies
3.7 Using Supervision in Unsupervised Training
3.8 Segmentation
3.9 References

 

4 Waveform Synthesis (A Generative Approach)
4.1 RF ML: Applications & When to Use
4.2 Algorithms & Architecture
4.3 Performance Assessment
4.4 Architecture Studies
4.5 Reinforcement Learning-Driven Design
4.6 Adversarial RF ML
4.7 References

 

5 Designing for RF Systems
5.1 RF ML: Applications & When to Use
5.2 Streaming Operations
5.3 Detection
5.4 Hybrid Solutions
5.5 Considering the Environment and Scenario
5.6 Control
5.7 Multi-Modal Considerations
5.8 References

 

6 Developing Robust RF ML Solutions
6.1 Trustworthy AI
6.2 Transfer Learning
6.3 Operational Challenges
6.4 Explainability
6.5 Confidence
6.6 References

 

7 RF Data and Augmentation
7.1 Challenges
7.2 RF ML Datasets
7.3 Collecting Data
7.4 Modeling, Simulation, and Synthetic Data Generation
7.5 Data Augmentation
7.6 Data Imbalance & Sampling Methods
7.7 References

 

8 Edge, Federated, and Continual Learning
8.1 RF ML: Applications & When to Use
8.2 Efficient Algorithms (Tiny ML)
8.3 A Note on Training
8.4 Federated Learning
8.5 Continual and Active Learning
8.6 Adaptive Control
8.7 Hardware
8.8 References

 

Appendix – Background
A.1 Artificial Neural Networks
A.2 Understanding What it Means to Learning
A.3 How Theory Impacts Design Decisions
A.4 References

 

List of Acronyms and Abbreviations
Author Biography
Index

  • Scott Kuzdeba

    has been leading the development of RF machine learning (ML) algorithms and systems for over 15 years. He has served in numerous roles including chief scientist, principal investigator, subject matter expert, and capture leader. Currently Dr. Kuzdeba is the director of the Edge and Spectral Artificial Intelligence group within the BAE Systems FAST Labs™ research and development organization. In this role, he works closely with governmental organizations (including DARPA, IARPA, and AFRL) and multiple university partners to develop new RF ML solutions to solve some of the defense industry’s most challenging problems. Dr. Kuzdeba frequently publishes peer reviewed papers, holds several patents within the RF ML field, and is an active member of the AOC, AAAI, and IEEE. He received his PhD in computational neuroscience from Boston University, where the inspiration for his artificial intelligence work stemmed from studying biological neural networks related to speech perception and articulation.

© 2024 Artech House