Skip to main navigation Skip to search Skip to main content

Time-multiplexed Weight Sharing of Photonic Neural Networks

  • Jiawei Zhang
  • , Eli A. Doris
  • , Weipeng Zhang
  • , Yusuf O. Jimoh
  • , Bhavin J. Shastri
  • , Paul Prucnal

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

Abstract

Silicon photonic neural networks often rely on thermal tuning of weights, limiting scaling for deep learning tasks. We demonstrate a time-domain weight sharing method that can reduce reconfigurations and energy by 6.6x without compromising accuracy.

Original languageEnglish (US)
Title of host publicationCLEO
Subtitle of host publicationScience and Innovations - Proceedings CLEO 2025
PublisherOptical Society of America
ISBN (Electronic)9781957171500
DOIs
StatePublished - 2025
Event2025 CLEO: Science and Innovations, CLEO-SI 2025 - Long Beach, United States
Duration: May 4 2025May 9 2025

Publication series

NameCLEO: Science and Innovations - Proceedings CLEO 2025

Conference

Conference2025 CLEO: Science and Innovations, CLEO-SI 2025
Country/TerritoryUnited States
CityLong Beach
Period5/4/255/9/25

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • Space and Planetary Science
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Instrumentation

Fingerprint

Dive into the research topics of 'Time-multiplexed Weight Sharing of Photonic Neural Networks'. Together they form a unique fingerprint.

Cite this