English

Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

Machine Learning 2022-11-30 v1 Emerging Technologies Neural and Evolutionary Computing

Abstract

We demonstrate transfer learning-assisted neural network models for optical matrix multipliers with scarce measurement data. Our approach uses <10\% of experimental data needed for best performance and outperforms analytical models for a Mach-Zehnder interferometer mesh.

Keywords

Cite

@article{arxiv.2211.16038,
  title  = {Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning},
  author = {Ali Cem and Ognjen Jovanovic and Siqi Yan and Yunhong Ding and Darko Zibar and Francesco Da Ros},
  journal= {arXiv preprint arXiv:2211.16038},
  year   = {2022}
}

Comments

2 pages, 2 figues, submitted to CLEO

R2 v1 2026-06-28T07:16:27.432Z