Publisher's Synopsis
This text investigates the ability of a neural network (NN) to learn how to control an unknown - generally nonlinear - system using data acquired on-line. The work presents real-time control applications, together with the theoretical analysis of algorithms developed to train neural networks. It provides: an analysis of local convergence and stability requirements of the two fast-learning algorithms developed by the author; a comprehensive survey of network topology and learning algorithms - particularly supervised learning; and a classification for NN control strategies. The book also analyzes and discusses various control strategies.