EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Nonlinear optical feature generator for machine learning

Mustafa Yildirim, Ilker Oguz, Fabian Kaufmann, Marc Reig Escalé, Rachel Grange, Demetri Psaltis, Christophe Moser

APL Photonics · 01.10.2023 · 8 (10)

DOI: 10.1063/5.0158611 ↗

Kurz gefasst

Fachartikel in der Zeitschrift APL Photonics, online erschienen am 04.10.2023. Verfasst von Mustafa Yildirim und 6 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020 Framework Program, Swiss National Science Foundation, Swiss National Science Foundation - Sinergia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern machine learning models use an ever-increasing number of parameters to train (175 × 109 parameters for GPT-3) with large datasets to achieve better performance. Optical computing has been rediscovered as a potential solution for large-scale data processing, taking advantage of linear optical accelerators that perform operations at lower power consumption. However, to achieve efficient computing with light, it remains a challenge to create and control nonlinearity optically rather than electronically. In this study, a reservoir computing approach (RC) is investigated using a 14-mm waveguide in LiNbO3 on an insulator as an optical processor to validate the benefit of optical nonlinearity. Data are encoded on the spectrum of a femtosecond pulse, which is launched into the waveguide. The output of the waveguide is a nonlinear transform of the input, enabled by optical nonlinearities. We show experimentally that a simple digital linear classifier using the output spectrum of the waveguide increases the classification accuracy of several databases by ∼10% compared to untransformed data. In comparison, a digital neural network (NN) with tens of thousands of parameters was required to achieve similar accuracy. With the ability to reduce the number of parameters by a factor of at least 20, an integrated optical RC approach can attain a performance on a par with a digital NN.

Förderung

  • Horizon 2020 Framework Program
  • Swiss National Science Foundation
  • Swiss National Science Foundation - Sinergia

Zitieren

APA

Yildirim, M., Oguz, I., Kaufmann, F., Escalé, M. R., Grange, R., Psaltis, D., & Moser, C. (2023). Nonlinear optical feature generator for machine learning. APL Photonics, 8(10). https://doi.org/10.1063/5.0158611

Vancouver

Yildirim M, Oguz I, Kaufmann F, Escalé MR, Grange R, Psaltis D, et al. Nonlinear optical feature generator for machine learning. APL Photonics. 2023;8(10). doi:10.1063/5.0158611

BibTeX
@article{Yildirim2023,
  author = {Yildirim, Mustafa and Oguz, Ilker and Kaufmann, Fabian and Escalé, Marc Reig and Grange, Rachel and Psaltis, Demetri and Moser, Christophe},
  title = {Nonlinear optical feature generator for machine learning},
  journal = {APL Photonics},
  year = {2023},
  volume = {8},
  number = {10},
  doi = {10.1063/5.0158611}
}
Kostenlos starten →