Associative Memories
After having introduced the different possiblities to realize the most important components of optical neural networks — interconnection and storage systems, threshold devices and optical processing configurations — it is time to put these components toge
- PDF / 59,334,288 Bytes
- 467 Pages / 481.89 x 691.654 pts Page_size
- 90 Downloads / 202 Views
Optical Neural Networks
Cornelia Denz
Optical Neural Networks Edited by Theo Tschudi
11 Vleweg
Die Deutsche Bibliothek - CIP-Einheitsaufnahme Denz, Cornelia: Optical neural networks: an introduction with special emphasize on photorefractive implementations 1 Cornelia Denz. Ed. by Theo Tschudi. - Braunschweig; Wiesbaden: Vieweg, 1998 (Optics and photonics)
Anschrift Dr. Cornelia Denz Institut für Angewandte Optik Technische Universität Darmstadt AG Photorefraktive Optik Hochschulstr. 6 D-64289 Darmstadt
Alle Rechte vorbehalten © Springer Fachmedien Wiesbaden 1998 Ursprünglich erschienen bei Friedr. Vieweg & Sohn Verlags gesellschaft mbH, BraunschwiegiWiebaden 1998. Softcover reprint of the hardcover 1st edition 1998
Das Werk einschließlich aller seiner Teile ist urheberrechtlich geschützt. Jede Verwertung außerhalb der engen Grenzen des Urheberrechtsgesetzes ist ohne Zustimmung des Verlags unzulässig und strafbar. Das gilt insbesondere für Vervielfältigungen, Übersetzungen, Mikroverfilmungen und die Einspeicherung und Verarbeitung in elektronischen Systemen.
http://www.vieweg.de
Umschlaggestaltung: Klaus Birk, Wiesbaden Gedruckt auf säurefreiem Papier
ISBN 978-3-663-12274-6 ISBN 978-3-663-12272-2 (eBook) DOI 10.1007/978-3-663-12272-2
Light is the first of painters. There is no object so foul that intense light will not make it beautiful - Ra/ph Wa/do Emerson -
VII
Preface In recent years, there has been a rapid expansion in the field of nonlinear optics as weIl as in the field of neural computing. Up to date, no one would doubt that nonlinear optics is one of the most promising fields of realizing large neural network models due to their inherent parallelism, the use of the speed of light and their ability to process two-dimensional data arrays without carriers or transformation bottlenecks. This is the reason why so many of the interesting applications of nonlinear optics - associative memories, Hopfield networks and self-organized nets - are realized in an all optical way using nonlinear optical processing elements. Both areas attracting people from a wide variety of disciplines and judged by the proliferation of published papers, conferences, international collaborations and enterprises, more people than ever before are now involved in research and applications in these two fields. These people all bring a different background to the area, and one of the aims of this book is to provide a common ground from which new development can grow. Another aim is to explain the basic concepts of neural computation as weIl as its nonlinear optical realizations to an interested audience. Therefore, the book is about the whole field of optical neural network applications, covering all the major approaches and their important results. Especially, it its an introduction that develops the concepts and ideas from their simple basics through their formulation into powerful experimental neural net systems. In writing this book, my objective was not to completely review the vast range of activity that can be actually
