Online training and pruning of photonic neural networks

Weipeng Zhang, Tengji Xu, Jiawei Zhang, Bhavin J. Shastri, Chaoran Huang, Paul Prucnal

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

Abstract

Photonic neural networks have unique weight-actuating mechanisms and manufacturing variations, resulting in a suboptimal performance by conventional offline training. By incorporating a power-pruning regularization term in the loss function, we demonstrate an online training method that can overcome manufacturing errors and minimize power consumption.

Original languageEnglish (US)
Title of host publication2023 IEEE Photonics Conference, IPC 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350347227
DOIs
StatePublished - 2023
Event2023 IEEE Photonics Conference, IPC 2023 - Orlando, United States
Duration: Nov 12 2023Nov 16 2023

Publication series

Name2023 IEEE Photonics Conference, IPC 2023 - Proceedings

Conference

Conference2023 IEEE Photonics Conference, IPC 2023
Country/TerritoryUnited States
CityOrlando
Period11/12/2311/16/23

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality
  • Control and Optimization
  • Atomic and Molecular Physics, and Optics

Keywords

  • Photonic neural network
  • neural network training

Fingerprint

Dive into the research topics of 'Online training and pruning of photonic neural networks'. Together they form a unique fingerprint.

Cite this