This text provides a clear and detailed survey of basic neural network architectures and learning rules. The authors emphasize mathematical analysis of networks, methods for training networks, and application of networks to practical engineering problems in pattern recognition, signal processing, and control systems. Background material, such as linear algebra, optimization, and stability, is provided. Simple building blocks are used to explain associative and competitive networks. They include feature maps, learning vector quantization, and adaptive resonance theory. Examples and solved problems are included with optional exercises incorporating the use of MATLAB. An instructor's manual is available for adopters of this text.
To obtain a copy of the Neural Network Design text or the Instructors Manual contact John Stovall at the University of Colorado Bookstore, phone 303-492-3648. Ask specifically for an instructor's manual if you are instructing a class and want one.
In addition, a set of MATLAB code files, transparency masters, and a set of video lectures are available. 重新获取随附软件
Martin T. Hagan, Oklahoma State University
Howard B. Demuth, University of Idaho
Mark Hudson Beale, MHB, Inc
Martin/Hagan (Distributed by the University of Colorado), 1996