Monte Carlo optimization for real-time magnetic domain learning in magneto-optical diffractive deep neural networks
Journal of the European Optical Society-Rapid Publications · 2026 · 22 (1) · 27
DOI: 10.1051/jeos/2026026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the European Optical Society-Rapid Publications, online erschienen am 23.04.2026. Verfasst von Fatima Zahra Chafi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
We propose an optimized algorithm using Monte Carlo Method (MCM) tailored for online learning in magneto-optical diffractive deep neural networks (MO-D 2 NN), a physical neural network platform where binary-weight are determined by magneto-optical modulation of light through the Faraday effect. Our derivative-free approach based MCM, iteratively adjusts the magnetic domain patterns to minimize cross-entropy loss without relying on gradients at a much lower computational cost. Our findings reveal that the MCM-based optimization algorithm serves as a robust and viable alternative to gradient descent-based training, achieving an accuracy of 96% for MNIST (Modified National Institute of Standard and Technology) handwritten digits classification with only a single hidden layer, highlighting its potential as a powerful approach for training MO-D 2 NN. We further validate its feasibility through physical implementation in an experimental optical setup, confirming its practical applicability for online image recognition tasks. We successfully demonstrate real-time learning of MO-D 2 NN using the MCM algorithm.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Chafi, F. Z., Matsuya, T., Sakaguchi, H., Watanabe, K., & Ishibashi, T. (2026). Monte Carlo optimization for real-time magnetic domain learning in magneto-optical diffractive deep neural networks. Journal of the European Optical Society-Rapid Publications, 22(1), 27. https://doi.org/10.1051/jeos/2026026
Vancouver
Chafi FZ, Matsuya T, Sakaguchi H, Watanabe K, Ishibashi T. Monte Carlo optimization for real-time magnetic domain learning in magneto-optical diffractive deep neural networks. Journal of the European Optical Society-Rapid Publications. 2026;22(1):27. doi:10.1051/jeos/2026026
BibTeX
@article{Chafi2026,
author = {Chafi, Fatima Zahra and Matsuya, Tomonao and Sakaguchi, Hotaka and Watanabe, Kanata and Ishibashi, Takayuki},
title = {Monte Carlo optimization for real-time magnetic domain learning in magneto-optical diffractive deep neural networks},
journal = {Journal of the European Optical Society-Rapid Publications},
year = {2026},
volume = {22},
number = {1},
pages = {27},
doi = {10.1051/jeos/2026026}
}
EUVIMED