Neural Network Engineering in Dynamic Control Systems - Couverture rigide

Couverture rigide

ISBN 10 : 354019973X ISBN 13 : 9783540199731

Editeur : Springer-Verlag Berlin and Heidelberg GmbH & Co. K, 1995

Synopsis

This study evaluates the state of the art in the area of neural networks from the engineering perspective. The book examines ways of improving the engineering involved in neural network modelling and control, so that the theoretical power of learning systems can be harnessed for practical applications. The book seeks to answer a number of questions, such as which network architecture for which application? Can constructive learning algorithms capture the underlying dynamics while avoiding overfitting? How can we introduce a priori knowledge or models into neural networks? Can experimental design and active learning be used automatically to create "optimal" training sets? And finally, how can we validate a neural network model?

Détails de l'édition

• Éditeur: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
• Date d'édition: 1995
• Langue: anglais
• ISBN 10: 354019973X
• ISBN 13: 9783540199731
• Reliure: Relié
• Nombre de pages: 296
• Éditeur: Hunt K. J., Etc., Irwin Graham R., Warwick K.
• Coordonnées du fabricant: non disponible
• Personne responsable: CMN Printpool Inh. Mathis Neumann; https://www.also.com/ec/cms5/en_6000/6000/index.jsp; ; Friedrich-Karl-Str. 9; 0; Hamburg; 22391; Allemagne