An optical learning network with amplitude detection

Chau Jern Cheng, Ken Y. Hsu, Tai Chiung Hsieh, Pochi Yeh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

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
PublisherSPIE
Pages488-499
Number of pages12
ISBN (Electronic)9780819410061
DOIs
Publication statusPublished - 1993 Jul 12
EventTopical Meeting on Optical Computing 1992 - Minsk, Belarus
Duration: 1992 Jun 291992 Jul 1

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume1806
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

OtherTopical Meeting on Optical Computing 1992
CountryBelarus
CityMinsk
Period92/6/2992/7/1

    Fingerprint

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Cheng, C. J., Hsu, K. Y., Hsieh, T. C., & Yeh, P. (1993). An optical learning network with amplitude detection. In F. V. Karpushko, G. V. Sinitsyn, S. P. Apanasevich, & A. M. Goncharenko (Eds.), Optical Computing (pp. 488-499). (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 1806). SPIE. https://doi.org/10.1117/12.147870