Leveraging multiplexed metasurfaces for multi-task learning with all-optical diffractive processors

Abstract: Diffractive Neural Networks (DNNs) leverage the power of light to enhance computational performance in machine learning, offering a pathway to high-speed, low-energy, and large-scale neural information processing. However, most existing DNN architectures are optimized for single tasks and thus lack the flexibility required for the simultaneous execution of multiple tasks within a unified artificial intelligence platform. In this work, we utilize the polarization and wavelength degrees of freedom of light to achieve optical multi-task identification using the MNIST, FMNIST, and KMNIST datasets. Employing bilayer cascaded metasurfaces, we construct dual-channel DNNs capable of simultaneously classifying two tasks, using polarization and wavelength multiplexing schemes through a meta-atom library. Numerical evaluations demonstrate performance accuracies comparable to those of individually trained single-channel, single-task DNNs. Extending this approach to three-task parallel recognition reveals an expected performance decline yet maintains satisfactory classification accuracies of greater than 80 % for all tasks. We further introduce a novel end-to-end joint optimization framework to redesign the three-task classifier, demonstrating substantial improvements over the meta-atom library design and offering the potential for future multi-channel DNN designs. Our study could pave the way for the development of ultrathin, high-speed, and high-throughput optical neural computing systems.

Standort
Deutsche Nationalbibliothek Frankfurt am Main
Umfang
Online-Ressource
Sprache
Englisch

Erschienen in
Leveraging multiplexed metasurfaces for multi-task learning with all-optical diffractive processors ; volume:13 ; number:24 ; year:2024 ; pages:4505-4517 ; extent:13
Nanophotonics ; 13, Heft 24 (2024), 4505-4517 (gesamt 13)

Urheber
Behroozinia, Sahar
Gu, Qing

DOI
10.1515/nanoph-2024-0483
URN
urn:nbn:de:101:1-2411111448461.962166382425
Rechteinformation
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Letzte Aktualisierung
15.08.2025, 07:33 MESZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.

Beteiligte

  • Behroozinia, Sahar
  • Gu, Qing

Ähnliche Objekte (12)