An optical learning network with amplitude detection

Chau Jern Cheng, Ken-Yuh Hsu, Tai Chiung Hsieh, Pochi Yeh

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations


An optical learning network using photorefractive holograms with grating amplitude detection is presented and demonstrated. The Stoke's principle for light is used to realize both bipolar weight changes and bipolar activities for perceptron learning. The bipolar detection is achieved by using a double Mach-Zehnder interferometer and an electronic subtractor at the output port. Experimental results show that a zero or near to zero threshold value, the network can be trained to dichotomize the input patterns.

Original languageEnglish
Title of host publicationOptical Computing
EditorsFedor V. Karpushko, George V. Sinitsyn, Sergey P. Apanasevich, Andrey M. Goncharenko
Number of pages12
ISBN (Electronic)9780819410061
StatePublished - 12 Jul 1993
EventTopical Meeting on Optical Computing 1992 - Minsk, Belarus
Duration: 29 Jun 19921 Jul 1992

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceTopical Meeting on Optical Computing 1992

Fingerprint Dive into the research topics of 'An optical learning network with amplitude detection'. Together they form a unique fingerprint.

Cite this