Artificial neural networks / Robert J. Schalkoff.

Includes bibliographical references and index.

1. Overview: Artificial Neural Networks and Neural Computing -- 2. Mathematical Fundamentals for ANN Study -- 3. Elementary ANN Building Blocks -- 4. Single-Unit Mappings and the Perceptron -- 5. Introduction to Neural Mappings and Pattern Associator Applications -- 6. Feedforward Networks and Training: Part 1 -- 7. Feedforward Networks, Part 2: Extensions and Advanced Topics -- 8. Recurrent Networks -- 9. Competitive and Self-Organizing Networks -- 10. Radial Basis Function (RBF) Networks and Time Delay Neural Networks (TDNNs) -- 11. Fuzzy Neural Networks Including Fuzzy Sets and Logic and ANN Implementations -- 12. ANN Hardware and Implementation Concerns.

Artificial Neural Networks brings together an identifiable core of ideas, techniques, and applications that characterize this emerging field. The text is intended for beginning graduate/advanced undergraduate students as well as practicing engineers and scientists.

The text is suitable for use in a one- or two-semester course and may be supplemented by individual student projects and readings from the literature. Numerous exercises are presented to challenge and motivate the reader to further explore relevant concepts. Many of these exercises can be expanded into projects and thesis work.

No previous experience in this field is assumed, although readers familiar with signal processing, linear algebra, pattern recognition, and other related areas will find the book easier to read. The book is meant to be largely self-contained and suitable for students in the disciplines of electrical and computer engineering, computer science, mathematics, physics, and related disciplines.

While the primary objective of the text is to provide a teaching tool, practicing engineers and scientists are likely to find the clear, concept-based treatment useful in updating their backgrounds.