Artificial Neural Networks: An Introduction to ANN Theory and Practice

P. J. Braspenning (auth.), P. J. Braspenning, F. Thuijsman, A. J. M. M. Weijters (eds.)3540594884, 9783540594888

This book presents carefully revised versions of tutorial lectures given during a School on Artificial Neural Networks for the industrial world held at the University of Limburg in Maastricht, Belgium.
The major ANN architectures are discussed to show their powerful possibilities for empirical data analysis, particularly in situations where other methods seem to fail. Theoretical insight is offered by examining the underlying mathematical principles in a detailed, yet clear and illuminating way. Practical experience is provided by discussing several real-world applications in such areas as control, optimization, pattern recognition, software engineering, robotics, operations research, and CAM.

---

Table of contents :
Introduction: Neural networks as associative devices….Pages 1-9
Backpropagation networks for Grapheme-Phoneme conversion: A non-technical introduction….Pages 11-36
Back Propagation….Pages 37-66
Perceptrons….Pages 67-81
Kohonen network….Pages 83-100
Adaptive Resonance Theory….Pages 101-117
Boltzmann Machines….Pages 119-129
Representation issues in Boltzmann machines….Pages 131-144
Optimisation networks….Pages 145-156
Local search in combinatorial optimization….Pages 157-174
Process identification and control….Pages 175-204
Learning controllers using neural networks….Pages 205-233
Key issues for successful industrial neural-network applications: An application in geology….Pages 235-245
Neural cognodynamics….Pages 247-271
Choosing and using a neural net….Pages 273-287