NEURAL NETWORK DESIGN provides a clear and detailed survey of fundamental neural network architectures and learning rules. In it, 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. The book incorporates necessary background material (such as linear algebra, optimization, and stability) to the extent it is needed. The book includes extensive coverage of performance learning, including the Widrow-Hoff rule and backpropagation. The authors describe several enhancements of backpropagation, such as the conjugate gradient and Levenberg-Marquardt variations. These techniques are illustrated with applications in pattern recognition, adaptive filtering, and function approximation. The authors use simple building blocks to explain associative and competitive networks, including feature maps, learning vector quantization, and adaptive resonance theory. Recurrent associative memory networks, such as the Hopfield network, are also discussed. All topics are systematically presented in a unified framework with a consistent notation. Detailed examples and numerous solved problems are included.
Optional exercises incorporating the use of MATLAB are built into each chapter, and a set of Neural Network Design Demonstrations make use of MATLAB to illustrate important concepts. In addition, the book's straightforward organization -- with each chapter divided into the following sections: Objectives, Theory and Examples, Summary of Results, Solved Problems, Epilogue, Further Reading, and Exercises -- makes it an excellent tool for learning and continued reference.
This book can be obtained from the University of Colorado Bookstore. Contact Matt at 303-492-3422.
Transparency Masters (You will need Stuffit Expander for the PDF Files)
Neural Network Design Demonstrations