Abstract

Some rules of the diffractive deep neural network (D²NN) are discovered. They reveal that the inner product of any two optical fields in D²NN is invariant and the D²NN acts as a unitary transformation for optical fields. If the output intensities of the two inputs are separated spatially, the input fields must be orthogonal. These rules imply that the D²NN is not only suitable for the classification of general objects but also more suitable for applications aimed at optical orthogonal modes. Our simulation shows the D²NN performs well in applications like mode conversion, mode multiplexing/demultiplexing, and optical mode recognition.

© 2022 Optica Publishing Group

Optical random micro-phase-shift DropConnect in a diffractive deep neural network

Yong-Liang Xiao, Sikun Li, Guohai Situ, and Jianxin Zhong
Opt. Lett. 47(7) 1746-1749 (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)

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)

Residual D²NN: training diffractive deep neural networks via learnable light shortcuts

Hongkun Dou, Yue Deng, Tao Yan, Huaqiang Wu, Xing Lin, and Qionghai Dai
Opt. Lett. 45(10) 2688-2691 (2020)

Optical random phase dropout in a diffractive deep neural network

Yong-Liang Xiao, Sikun Li, Guohai Situ, and Zhisheng You
Opt. Lett. 46(20) 5260-5263 (2021)