Gupta M.M., Jin L., Homma N. Static and Dynamic Neural Networks. From Fundamentals to Advanced Theory

IEEE Press/John Wiley, 2003, -751 p.The human cognitive faculty - the carbon-based computer - has a vast network of processing cells called neural networks, and this science of neural networks has inspired many researchers in biological as well as nonbiological fields. This inspiration has generated keen interest among engineers, computer scientists, and mathematicians for developing some basic mathematical models of neurons, and to use the collective actions of these neural models to find the solutions to many practical problems. The concepts evolved in this realm have generated a new field of neural networks.
The idea for this textbook on neural networks was conceived during the classroom teachings and research discussions in the laboratory as well as at international scientific meetings. We are pleased to see that our several years of work is finally appearing in the form of this book. This book, of course, has gone through several phases of writings and rewritings over the last several years.
The contents of this book, entitled Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory, follows a logical style providing the readers the basic concepts and then leading them to some advanced theory in the field of neural networks.
The mathematical models of a basic neuron, the elementary components used in the design of a neural network, are a fascinating blend of heuristic concepts and mathematical rigor. It has become a subject of large interdisciplinary areas of teaching and research, and these mathematical concepts have been successfully applied in finding some robust solutions for problems evolving in the many fields of science and technology. Our own studies have been in the fields of neurocontrol systems, neurovision systems, robotic systems, neural chaotic systems, pattern recognition, and signal and image processing.Part I Foundations of Neural Networks.
Neural Systems: An Introduction.
Biological Foundations of Neuronal Morphology.
Neural Units: Concepts, Models, and Learning.
Part II Static Neural Networks.
Multilayered Feedforward Neural Networks (MFNNs) and Backpropagation Learning Algorithms.
Advanced Methods for Learning and Adaptation in MFNNs.
Radial Basis Function Neural Networks.
Function Approximation Using Feedforward Neural Networks.
Part III Dynamic Neural Networks.
Dynamic Neural Units (DNUs): Nonlinear Models and Dynamics.
Continuous-Time Dynamic Neural Networks.
Learning and Adaptation in Dynamic Neural Networks.
Stability of Continuous-Time Dynamic Neural Networks.
Discrete-Time Dynamic Neural Networks and Their Stability.
Part IV Some Advanced Topics in Neural Networks.
Binary Neural Networks.
Feedback Binary Associative Memories.
Fuzzy Sets and Fuzzy Neural Networks.