Description
The high-speed capabilities and learning abilities of neural networks can be applied to quickly solving numerous complex optimization problems in electromagnetics, and this book shows you how. Even if you have no background in neural networks, this book helps you understand the basics of each main network architecture in use today, including its strengths and limitations. Moreover, it gives you the knowledge you need to identify situations when the use of neural networks is the best problem-solving option. Organized in a modular format that lets you find and use the information you need fast, the book includes five full chapters that zero-in on specific neural network applications. Included are chapters on antennas, remote sensing and target classification, microwave devices and circuit modeling, and real-time performance systems for military and civilian systems, such as GPS and mobile communications. You also see how neural networks can be used in conjunction with other methods, such as the finite element method, the finite difference method, and the method of moments. More than 700 equations and over 200 illustrations are included, and MATLAB code for applications using neural network technology is found in relevant chapters.
Table Of Contents
Preface. Acknowledgments. Introduction to Neural Networks - Preliminaries. Benefits of Neural Networks. Models of a Neuron. Types of Activation Function. Neural Network Architectures. Learning Procedures. Learning Tasks. Knowledge Representation. Brief History of Neural Networks. Why Neural Networks in Electromagnetics.; Single-Layer and Multilayer Perceptron Networks -Introduction. The Single-Layer Perceptron. Perceptron Learning Algorithm. Adaline Network. Multilayer Perceptron. The Back-Propagation Algorithm. Issues With Back-Propagation Learning. Variations of the Back-Propagation Algorithm. The Mulitlayer Perceptron Neural Network for an Automatic Target Recognition Application. MATLAB Code.; Radial Basis Function Networks-Kohonen Networks -Introduction. Preliminaries of Radial Basis Function Neural Networks. Learning Strategies With Radial Basis Function Neural Networks. A Radial Basis Function Neural Network Algorithm, A Radial Basis Function Neural Network Example. Comparison of Radial Basis Function Neural Network Learning Strategies. Issues With Radial Basis Function Neural Network Learning. The General Regression Neural Network (GRNN). MATLAB Code.; Adaptive Resonance Theory Neural Networks -Introduction. The Fuzzy ARTMAP Neural Network. Templates in Fuzzy ARTMAP: A Geometrical Interpretation. Example. Convergence Speed of Fuzzy ARTMAP. Order of Search in Fuzzy ARTMAP. Applications of Fuzzy ARTMAP. MATLAB Code.; Recurrent Neural Networks -Introduction. Preliminaries of Associative Memories. The Hopfield Model. Associative Memory Application of the Hopfield Neural Network. Discussion. Optimization Problems Using the Hopfield Neural Network. A Problem in Communications Using the Hopfield Neural Network. The RTRL Neural Network. RTRL NN Examples. The Recurrent Time Recurrent Learning Neural Network for Channel Equalization. The Elman Neural Network. Elman Neural Network Examples. Angle of Arrival Estimation Using Elman Networks. MATLAB Code.; Applications in Antennas -Introduction. Design of Gratings and Frequency Selective Surfaces. Neural Network-Based Adaptive Array Antennas. Beam Shaping With Antenna Arrays. Aperture Antenna Shape Prediction. Reflector Surface Error Compensation. Resonance Frequency of Triangular Microstrip Antennas. Design of Multilayer Phased Array Antennas; Applications in Radar and Remote Sensing -Introduction. Radar Target Classification. Classification of Radar Clutter. Remote Sensing.; Applications in Mobile Communications -Introduction. Adaptive Antenna Array Processing. Neural Network-Based Direction Finding. Direction of Arrival for Multiple Sources Using Multilayer Neural Networks. Adaptive Nulling and Steering. Neural Network-Based Interference Cancellation.; Applications in Microwave Circuits and Devices -Introduction. Simulation and Optimization of Microwave Devices and Circuits. Modeling of Passive Devices for MMIC Design. Speeding Up and Configuring the Optimum Size for a Neural Network. A Modular, Knowledge-Based Development of Libraries of Neural Network Models.; Applications in Computational Electromagnetics -Introduction. Finite Element Applications. A General Neural Network Representation of FEM. A Neural Network Approach of the Method of Moments. Combination of the Piecewise Harmonic Balance Technique and Neural Networks.; About the Authors. Index.;
Author
-
Christos Christodoulou
Christos G. Christodoulou is a Fellow member of IEEE and a distinguished professor of electrical and computer engineering at the University of New Mexico. He is the recipient of the 2010 IEEE John Krauss Antenna Award for his work on reconfigurable fractal antennas, the Lawton-Ellis Award and the Gardner Zemke Professorship at the University of New Mexico. He holds a M.S. and a Ph.D. in Electrical Engineering from North Carolina State University. Christos is the series editor of antennas at Artech House.
-
Michael Georgiopoulos
Michael Georgiopoulos is an associate professor in the Department of Electrical and Computer Engineering at the University of New Mexico. The author of more than 90 papers on theoretical and application issues pertaining to neural networks, he holds a M.S. and a Ph.D. in Electrical Engineering from the University of Connecticut at Storrs.