Principles of Artificial Neural Networks

Graupe, Daniel

ISBN 10: 9810225164 / ISBN 13: 9789810225162

Edité par World Scientific Pub Co Inc, 1997

A propos de cet article

Clean With No Highlighting Or Marks Inside. 238 Pages With The Index. Hardcover With A Dust Jacket.books are NOT signed. We will state signed at the description section. we confirm they are signed via email or stated in the description box. - Specializing in academic, collectiblle and historically significant, providing the utmost quality and customer service satisfaction. For any questions feel free to email us. N° de réf. du vendeur 027875

Détails bibliographiques

Titre : Principles of Artificial Neural Networks

Éditeur : World Scientific Pub Co Inc

Date d'édition : 1997

Reliure : Hardcover

Etat : Fine

Etat de la jaquette : Fine

Edition : 1st Edition.

A propos de ce titre

Synopsis :

This textbook is intended for a first-year graduate course on Artificial Neural Networks. It assumes no prior background in the subject and is directed to MS students in electrical engineering, computer science and related fields, with background in at least one programming language or in a programming tool such as Matlab, and who have taken the basic undergraduate classes in systems or in signal processing.The uniqueness of the book is in the breadth of its coverage over the range of all major artificial neural network approaches and in extensive hands-on case-studies on each and every neural network considered. These detailed case studies include complete program print-outs and results and deal with a range of problems, to illustrate the reader's ability to solve problems ranging from speech recognition, character recognition to control and signal processing problems, all on the basis of following the present text. Another unique aspect of the text is its coverage of important new topics of recurrent (time-cycling) networks and of large memory storage and retrieval problems.The text also attempts to show the reader how he can modify or combine one or more of the neural networks covered, to tailor them to a given problem which does not appear to fit any of the more standard designs, as is very often the case.