This book is intended to be a practical guide for students, engineers, and researchers in electromagnetics with minimal background in machine learning. The book contains 9 chapters and is broken into two main parts. Part I contains the first five chapters that cover the theoretical principles of the most common machine learning architectures and algorithms used today in electromagnetics and other applications. These algorithms include support vector machines, Gaussian processing for signal processing, kernel methods for antenna arrays, neural networks, deep learning for computational electromagnetics, and reinforcement learning. Each chapter starts from very basic principles and it progresses to the latest developments in the area of the specific ML algorithms and architectures. The chapters are supported by several examples for the reader to understand the details of each ML algorithm and figure out how it can potentially be applied to any engineering problem.
Part II, consists of the next following 4 chapters that provide detailed applications of the algorithms, covered in part I, in a variety of electromagnetic problems, such as in antenna array beamforming, angle of arrival detection, computational electromagnetics, antenna optimization, reconfigurable antennas, cognitive radio and other aspects of electromagnetic design. In the last chapter examples of how some of these algorithms have been implement of various microprocessors are also described. These chapters are new applications of ML algorithms that have not been implement before in the area of electromagnetics.
Machine learning (ML) is the study of algorithms that utilize learning from previous experience to enhance accuracy over time and improve decision-making. ML has already been applied in a variety of applications, especially in areas of engineering and computer science that involve data analysis and fields that lack closed-form mathematical solutions. These applications rely mainly on machine learning algorithms to implement functions of particular devices that cannot be achieved otherwise. Today, there are several practical implementations of various ML algorithms in robots, drones or other autonomous vehicles, in data mining, face recognition, stock market prediction, and target classification for security and surveillance, just to name a few. Moreover, machine learning has been used to optimize the design of a variety of engineering products in an autonomous, reliable, and efficient way.
Classic and state of the art machine learning algorithms have been used practically from the inception of this discipline in signal processing, communication and ultimately in electromagnetics, namely in antenna array processing and microwave circuit design, remote sensing and radar. The advancements in machine learning of the last two decades, in particular in kernel methods and deep learning, together with the progress in the computational power of commercially available computation devices and their associated software, made many ML algorithms and architectures possible to apply in practice in a plethora of applications.
This book is intended to give a comprehensive overview of the state of the art of known ML approaches in a way that the reader can implement them right away by taking advantage of publicly available Matlab and Python ML libraries and also by understanding the theoretical background behind these algorithms.
In general, this book contains 9 chapters and is broken into two main parts. Part I contains the first five chapters that cover the theoretical principles of the most common machine learning architectures and algorithms used today in electromagnetics and other applications. These algorithms include support vector machines, Gaussian processing for signal processing, kernel methods for antenna arrays, neural networks, deep learning for computational electromagnetics, and reinforcement learning. Each chapter starts from very basic principles and it progresses to the latest developments in the area of the specific ML algorithms and architectures. The chapters are supported by several examples for the reader to understand the details of each ML algorithm and figure out how it can potentially be applied to any engineering problem.
Part II, consists of the next following 4 chapters that provide detailed applications of the algorithms, covered in part I, in a variety of electromagnetic problems, such as in antenna array beamforming, angle of arrival detection, computational electromagnetics, antenna optimization, reconfigurable antennas, cognitive radio and other aspects of electromagnetic design. In the last chapter examples of how some of these algorithms have been implement of various microprocessors are also described. These chapters are new applications of ML algorithms that have not been implement before in the area of electromagnetics.
This book is intended to be a practical guide for students, engineers, and researchers in electromagnetics with minimal background in machine learning. We hope that the readers find in this book the necessary tools and examples that can help to them in applying the field of machine learning to some of their research problems. This book can also serve as a basic reference book for courses such as “Machine Learning Algorithms” , “Advanced Topics in Electromagnetics”, “Applications of Machine Learning in Antenna Array Processing,” and others.
What are some problems your book can help technical professionals solve?
A variety of electromagnetic problems, such as:
- antenna array beamforming
- angle of arrival detection
- computational electromagnetics
- reconfigurable antennas
- cognitive radio
What are important Features of your book and what are the Specific Benefits a buyer can expect to derive from those Features?
Feature: New Machine Learning Algorithms
Benefit: Easy to follow new algorithms that cannot be found in any other book
Feature: New applications in Electromagnetics
Benefit: Learn how these algorithms can be applied to a variety of Electromagnetic applications
Feature: No prior knowledge of Machine learning is required
Benefit: Good book to have to start learning about Machine learning algorithms
Please name the audiences at which this book is aimed. Why is the book appropriate for this audience?
- Professors and researchers: Learn how these new machine algorithms can be applied in their area of research
- Graduate students: Learn how these new machine algorithms can be applied in their area of research
- Research Institutes/Agencies such as NASA, Air Force, Sandia National Labs, etc.
Click here for more information or to order.
