Optoelectronic multilayer network

Alan Yamamura, Seiji Kobayashi, Mark Neifeld, Demetri Psaltis

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

Hybrid optoelectronic implementations combine the strength of optics in communications with that of electronics in computation. The authors describe a multilayer feedforward neural network implementation using neurons (computational elements) and synapses (connections between neurons) fabricated on an integrated circuit. Each synapse contains a photodetector thus allowing weights governing the connections to be accessed holographically from an optical disk. The authors have written holograms onto 5 1/4 inch reflective disks using a prototype Sony system.

Original languageEnglish (US)
Pages (from-to)152-153
Number of pages2
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume1359
StatePublished - 1990
Externally publishedYes
Event1990 International Topical Meeting on Optical Computing - OC '90 - Kobe, Jpn
Duration: Apr 8 1990Apr 12 1990

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Optoelectronic multilayer network'. Together they form a unique fingerprint.

Cite this