Neural Network Design (2nd Edition) - Couverture souple

Hagan, Martin T; Demuth, Howard B; Beale, Mark H; De Jesús, Orlando

Couverture souple

ISBN 10 : 0971732116 ISBN 13 : 9780971732117

Editeur : Martin Hagan, 2014

A propos du livre

Biographie de l'auteur :

Martin T. Hagan (Ph.D. Electrical Engineering, University of Kansas) has taught and conducted research in the areas of control systems and signal processing for the last 35 years. For the last 25 years his research has focused on the use of neural networks for control, filtering and prediction. He is a Professor in the School of Electrical and Computer Engineering at Oklahoma State University and a co-author of the Neural Network Toolbox for MATLAB. Howard B. Demuth (Ph.D. Electrical Engineering, Stanford University) has twenty-three years of industrial experience, primarily at Los Alamos National Laboratory, where he helped design and build one of the world's first electronic computers, the "MANIAC." Demuth has fifteen years teaching experience as well. He is co-author of the Neural Network Toolbox for MATLAB and currently teaches a Neural Network course for the University of Colorado at Boulder. Mark Hudson Beale (B.S. Computer Engineering, University of Idaho) is a software engineer with a focus on artificial intelligence algorithms and software development technology. Mark is co-author of the Neural Network Toolbox for MATLAB and provides related consulting through his company, MHB Inc., located in Hayden, Idaho. Orlando De Jesús (Ph.D. Electrical Engineering, Oklahoma State University) has twenty-four years of industrial experience, with AETI C.A. in Caracas, Venezuela, Halliburton in Carrollton, Texas and is currently working as Engineering Consultant in Frisco, Texas. Orlando’s dissertation was a basis for the dynamic network training algorithms in the Neural Network Toolbox for MATLAB.

Présentation de l'éditeur :

This book, by the authors of the Neural Network Toolbox for MATLAB, provides a clear and detailed coverage of fundamental neural network architectures and learning rules. In it, the authors emphasize a coherent presentation of the principal neural networks, methods for training them and their applications to practical problems. Features Extensive coverage of training methods for both feedforward networks (including multilayer and radial basis networks) and recurrent networks. In addition to conjugate gradient and Levenberg-Marquardt variations of the backpropagation algorithm, the text also covers Bayesian regularization and early stopping, which ensure the generalization ability of trained networks. Associative and competitive networks, including feature maps and learning vector quantization, are explained with simple building blocks. A chapter of practical training tips for function approximation, pattern recognition, clustering and prediction, along with five chapters presenting detailed real-world case studies. Detailed examples and numerous solved problems. Slides and comprehensive demonstration software can be downloaded from hagan.okstate.edu/nnd.html.

À propos de cette édition

• Éditeur: Martin Hagan
• Date d'édition: 2014
• ISBN 10: 0971732116
• ISBN 13: 9780971732117
• Reliure: Broché
• Numéro d'édition: 2
• Nombre de pages: 800