English

LuxNAS: A Coherent Photonic Neural Network Powered by Neural Architecture Search

Optics 2025-03-06 v1 Emerging Technologies

Abstract

We demonstrate a novel coherent photonic neural network using tunable phase-change-material-based couplers and neural architecture search. Compared to the MZI-based Clements network, our results indicate 85% reduction in the network footprint while maintaining the accuracy.

Keywords

Cite

@article{arxiv.2503.03731,
  title  = {LuxNAS: A Coherent Photonic Neural Network Powered by Neural Architecture Search},
  author = {Amin Shafiee and Febin Sunny and Sudeep Pasricha and Mahdi Nikdast},
  journal= {arXiv preprint arXiv:2503.03731},
  year   = {2025}
}

Comments

Paper accepted and to be presented at CLEO 2025