Abstract

Diffractive deep neural networks (D2NNs) have demonstrated their importance in performing various all-optical machine learning tasks such as classification and segmentation. However, current D2NNs can only detect spatial domain intensity information. They cannot solve problems that rely on frequency information, such as laser linewidth compression. We propose a new D2NN architecture that fully exploits frequency domain information. We demonstrate that only frequency domain D2NN (OF-D3NN) can be trained using deep learning algorithms and be successfully integrated into a free-space optical communications system (FSO) for information recovery.

© 2023 Optica Publishing Group

Review of diffractive deep neural networks

Yichen Sun, Mingli Dong, Mingxin Yu, Xiaolin Liu, and Lianqing Zhu
J. Opt. Soc. Am. B 40(11) 2951-2961 (2023)

Multi-wavelength diffractive neural network with the weighting method

Jianan Feng, Hang Chen, Dahai Yang, Junbo Hao, Jie Lin, and Peng Jin
Opt. Express 31(20) 33113-33122 (2023)

Spatiotemporal diffractive deep neural networks

Junhe Zhou, Haoqian Pu, and Jiaxin Yan
Opt. Express 32(2) 1864-1877 (2024)

Nonlinear Fourier transform receiver based on a time domain diffractive deep neural network

Junhe Zhou, Qingsong Hu, and Haoqian Pu
Opt. Express 30(21) 38576-38586 (2022)

Magneto-optical diffractive deep neural network

Takumi Fujita, Hotaka Sakaguchi, Jian Zhang, Hirofumi Nonaka, Satoshi Sumi, Hiroyuki Awano, and Takayuki Ishibashi
Opt. Express 30(20) 36889-36899 (2022)