Modeling of Optical Matrix Multipliers Using Transposed Convolutional Neural Networks

Ali Cem, Siqi Yan, Uiara Celine De Moura, Yunhong Ding, Darko Zibar, Francesco Da Ros

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

57 Downloads (Pure)

Abstract

We demonstrate a data-driven model for optical matrix multipliers utilizing Mach-Zehnder interferometer meshes. For a fabricated chip, a transposed convolutional neural network model learns from experimental measurements offline and predicts the weights across 100 frequency channels in the C-band with high precision (RMSE<0.8 dB).
Original languageEnglish
Title of host publicationProceedings of 2022 IEEE Photonics Conference
Number of pages2
PublisherIEEE
Publication date17 Nov 2022
Article number9975676
ISBN (Print)978-1-6654-3488-1
DOIs
Publication statusPublished - 17 Nov 2022
Event2022 IEEE Photonics Conference - Hyatt Regency Vancouver Hotel, Vancouver, Canada
Duration: 13 Nov 202217 Nov 2022

Conference

Conference2022 IEEE Photonics Conference
LocationHyatt Regency Vancouver Hotel
Country/TerritoryCanada
CityVancouver
Period13/11/202217/11/2022

Keywords

  • Weight measurement
  • Integrated optics
  • Optical interferometry
  • Optical device fabrication
  • Optical computing
  • Predictive models
  • Adaptive optics

Fingerprint

Dive into the research topics of 'Modeling of Optical Matrix Multipliers Using Transposed Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this