EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Nonlinear All-Optical Diffractive Deep Neural Network with 10.6 μm Wavelength for Image Classification

Yichen Sun, Mingli Dong, Mingxin Yu, Jiabin Xia, Xu Zhang, Yuchen Bai, Lidan Lu, Lianqing Zhu

International Journal of Optics · 27.02.2021 · 2021 · 1-16

DOI: 10.1155/2021/6667495 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Optics, erschienen am 27.02.2021. Verfasst von Yichen Sun und 7 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Municipal Education Commission, Programme of Introducing Talents of Discipline to Universities, Connotation Development Project of Beijing Information Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A photonic artificial intelligence chip is based on an optical neural network (ONN), low power consumption, low delay, and strong antiinterference ability. The all-optical diffractive deep neural network has recently demonstrated its inference capabilities on the image classification task. However, the size of the physical model does not have miniaturization and integration, and the optical nonlinearity is not incorporated into the diffraction neural network. By introducing the nonlinear characteristics of the network, complex tasks can be completed with high accuracy. In this study, a nonlinear all-optical diffraction deep neural network (N-D2NN) model based on 10.6 μm wavelength is constructed by combining the ONN and complex-valued neural networks with the nonlinear activation function introduced into the structure. To be specific, the improved activation function of the rectified linear unit (ReLU), i.e., Leaky-ReLU, parametric ReLU (PReLU), and randomized ReLU (RReLU), is selected as the activation function of the N-D2NN model. Through numerical simulation, it is proved that the N-D2NN model based on 10.6 μm wavelength has excellent representation ability, which enables them to perform classification learning tasks of the MNIST handwritten digital dataset and Fashion-MNIST dataset well, respectively. The results show that the N-D2NN model with the RReLU activation function has the highest classification accuracy of 97.86% and 89.28%, respectively. These results provide a theoretical basis for the preparation of miniaturized and integrated N-D2NN model photonic artificial intelligence chips.

Förderung

  • Beijing Municipal Education Commission
  • Programme of Introducing Talents of Discipline to Universities
  • Connotation Development Project of Beijing Information Science and Technology

Zitieren

APA

Sun, Y., Dong, M., Yu, M., Xia, J., Zhang, X., Bai, Y., Lu, L., & Zhu, L. (2021). Nonlinear All-Optical Diffractive Deep Neural Network with 10.6 μm Wavelength for Image Classification. International Journal of Optics, 2021, 1-16. https://doi.org/10.1155/2021/6667495

Vancouver

Sun Y, Dong M, Yu M, Xia J, Zhang X, Bai Y, et al. Nonlinear All-Optical Diffractive Deep Neural Network with 10.6 μm Wavelength for Image Classification. International Journal of Optics. 2021;2021:1-16. doi:10.1155/2021/6667495

BibTeX
@article{Sun2021,
  author = {Sun, Yichen and Dong, Mingli and Yu, Mingxin and Xia, Jiabin and Zhang, Xu and Bai, Yuchen and Lu, Lidan and Zhu, Lianqing},
  title = {Nonlinear All-Optical Diffractive Deep Neural Network with 10.6 μm Wavelength for Image Classification},
  journal = {International Journal of Optics},
  year = {2021},
  volume = {2021},
  pages = {1--16},
  doi = {10.1155/2021/6667495}
}
Kostenlos starten →