CaltechAUTHORS
  A Caltech Library Service

Optical multilayer neural networks

Psaltis, Demetri and Qiao, Yong (1991) Optical multilayer neural networks. In: Optical Information Processing Systems and Architectures III. Proceedings of SPIE. No.1564. Society of Photo-optical Instrumentation Engineers (SPIE) , Bellingham, WA, pp. 489-494. ISBN 9780819406927. https://resolver.caltech.edu/CaltechAUTHORS:20190221-110520860

[img] PDF - Published Version
See Usage Policy.

276Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190221-110520860

Abstract

In order to implement fully adaptive optical multilayer neural networks, a number of issues involving both learning algorithms and device technologies need to be addressed. In this paper, we present some important modifications to existing learning algorithms that serve to simplify optical architectures and allow the use of simple optical devices.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1117/12.49735DOIArticle
Additional Information:© 1991 Society of Photo-Optical Instrumentation Engineers (SPIE). This work was supported by DARPA and the Air Force Office of Scientific Research.
Funders:
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA)UNSPECIFIED
Air Force Office of Scientific Research (AFOSR)UNSPECIFIED
Series Name:Proceedings of SPIE
Issue or Number:1564
Record Number:CaltechAUTHORS:20190221-110520860
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190221-110520860
Official Citation:Demetri Psaltis and Yong Qiao "Optical multilayer neural networks", Proc. SPIE 1564, Optical Information Processing Systems and Architectures III, (1 November 1991); doi: 10.1117/12.49735; https://doi.org/10.1117/12.49735
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:93080
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:28 Feb 2019 23:53
Last Modified:03 Oct 2019 20:51

Repository Staff Only: item control page