Neural networks are one of the fast-growing paradigms for learning systems with a wide variety of potential applications in industry. In particular there are general results which prove the universal applicability of neural networks to many problems. There is also an ever greater understanding of the underlying manner in which tasks such as classification can be solved optimally by this host of techniques. Through the application of ideas of statistics, dynamical systems theory and information theory the methods are likely to become ever more effective for solving problems previously found to be difficult to tackle using standard techniques. This book compares and contrasts the academic theory and the industrial reality, with case studies and latest research findings from international experts. The contributions describe application areas including finance, digital data transmission, hybrid systems, automotive and aerospace industries, pattern analysis in clinical psychiatry, time series prediction, and genetic and neural algorithms. This book demonstrates the vigour and strength of the subject in solving hard problems and as such will be of great interest to all researchers and professionals with an interest in neural networks.

InhaltsangabePartial table of contents:Modelling and Controller Design of an EGR Solenoid Valve using Neural Networks (M. Arain).Estimating Helicopter Strain using a Neural Network Approach (A. Vella et al.).Neural Networks for Texture Classification (J. Boyce & J. Haddon).Visualizing Nuclear Magnetic Resonance Spectra with Self-Organizing Neural Networks (A. Koski, et al).A Clustering Algorithm to Produce Context Rich Networks (N. Allott, et al.).Neural Networks in VLSI Hardware (T. Clarkson).Optimal VLSI Implementation of Neural Networks (V. Beiu).New Avenues in Neural Networks (J. Taylor).Index.