Static and Dynamic Neural Networks

Provides comprehensive treatment of the theory of both static and
dynamic neural networks.

• Theoretical concepts are illustrated by reference to practical
  examples Includes end-of-chapter exercises and end-of-chapter
  exercises.

*An Instructor Support FTP site is available from the Wiley
editorial department.

Auteur
MADAN M. GUPTA is a professor in the Intelligent Systems Research Laboratory at the University of Saskatchewan, Canada. He received a BE from the Birla Institute of Technology and Science, Pilani, India, and a PhD from the University of Warwick, Canada. A Fellow of the IEEE and the SPIE, Professor Gupta has been awarded the Kaufmann Prize Gold Medal for Research in the field of fuzzy logic.
LIANG JIN received a BS and MSc in electrical engineering from the Changsha Institute of Technology, China, and a PhD in electrical engineering from the Chinese Academy of Space Technology. He is a senior member of the technical staff at Agere Systems in Allentown, Pennsylvania.
NORIYASU HOMMA earned a BA, MA, and PhD in electrical and communication engineering from Tohoku University, Japan, where he is an associate professor. He is currently a visiting professor at the Intelligent Systems Research Laboratory, College of Engineering, University of Saskatchewan, Canada.

Texte du rabat
A solid introduction to the concepts and advanced applications of neural networks Since the 1980s, the field of neural networks has undergone exponential growth. Robots in manufacturing, mining, agriculture, space and ocean exploration, and health sciences are just a few examples of the challenging applications where human-like attributes such as cognition and intelligence are playing an important role. Neural networks and related areas such as fuzzy logic and soft-computing in general are also contributing to complex decision-making in such fields as health sciences, management, economics, politics, law, and administration. In the future, robots could evolve into electro-mechanical systems with cognitive skills approaching human intelligence.

With a fascinating blend of heuristic concepts and mathematical rigor, Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory outlines the basic concepts behind neural networks and leads the reader onward to more advanced theory and applications. Pedagogically sound and clearly written, this text discusses:

• Neuronal morphology and neuro-computational systems
• Threshold logic, adaptation, and learning
• Static neural networks–MFNNs, XOR Neural Networks, and Backpropagation Algorithms
• Dynamic neural networks–both continuous-time and discrete-time
• Binary neural networks, feedback binary associative memories, fuzzy sets, and other advanced topics
  Thoroughly surveying the many-faceted and increasingly influential field of neural networks, this is a valuable reference for both practitioner and student.

Résumé
Provides comprehensive treatment of the theory of both static and dynamic neural networks.

• Theoretical concepts are illustrated by reference to practical examples Includes end-of-chapter exercises and end-of-chapter exercises.
  *An Instructor Support FTP site is available from the Wiley editorial department.

Contenu
Foreword: Lotfi A. Zadeh. Preface.

Acknowledgments.

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 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.

References and Bibliography.

Appendix A: Current Bibliographic Sources on Neural Networks.

Index.