Principles of Neurocomputing for Science and Engineering - Softcover

Ham, Fredric; Kostanic, Ivica

9780071181617: Principles of Neurocomputing for Science and Engineering

Softcover

ISBN 10: 007118161X ISBN 13: 9780071181617

Publisher: McGraw-Hill Education, 2001

This exciting new text covers artificial neural networks, but more specifically, neurocomputing. Neurocomputing is concerned with processing information, which involves a learning process within an artificial neural network architecture. This neural architecture responds to inputs according to a defined learning rule and then the trained network can be used to perform certain tasks depending on the application. Neurocomputing can play an important role in solving certain problems such as pattern recognition, optimization, event classification, control and identification of nonlinear systems, and statistical analysis.

"Principles of Neurocomputing for Science and Engineering," unlike other neural networks texts, is written specifically for scientists and engineers who want to apply neural networks to solve complex problems. For each neurocomputing concept, a solid mathematical foundation is presented along with illustrative examples to accompany that particular architecture and associated training algorithm.

The book is primarily intended for graduate-level neural networks courses, but in some instances may be used at the undergraduate level. The book includes many detailed examples and an extensive set of end-of-chapter problems.

"synopsis" may belong to another edition of this title.

Book Description:

This exciting new book covers artificial neural networks, but more specifically, neurocomputing. Neurocomputing is concerned with processing information, which involves a learning process within an artificial neural network architecture. Neurocomputing can play an important role in solving certain problems such as pattern recognition, optimization, event classification, control and identification of nonlinear systems, and statistical analysis. For each neurocomputing concept, a solid mathematical foundation is presented along with illustrative examples to accompany that particular architecture and associated training algorithm. The book includes many detailed examples and an extensive set of end-of-chapter problems. Key Features: *The book is divided into two major parts: Chapter 1-5 cover fundamental neurocomputing concepts and selected neural network architectures and learning rules; Chapter 6-10 cover applications of neurocomputing. An appendix includes a brief description of random variables and stochastic processes in relation to neurocomputing. *Most training algorithms are highlighted in the book so they can be easily referenced *some of the training algorithms have an accompanying MATLAB function implementation referenced in the book. These are highlighted by a computer icon. The code is realtively short and can be quickly entered into MATLAB.

About the Author:

Fred Ham is a professor at the Florida Institute of Technology.

"About this title" may belong to another edition of this title.