Abstract

Recent progress on optical neural networks (ONNs) heralds a new future for efficient deep learning accelerators, and novel, to the best of our knowledge, architectures of optical convolutional neural networks (CNNs) provide potential solutions to the widely adopted convolutional models. So far in optical CNNs, the data patching (a necessary process in the convolutional layer) is mostly executed with electronics, resulting in a demand for large input modulator arrays. Here we experimentally demonstrate an optical patching scheme to release the burden of electronic data processing and to cut down the scale of the input modulator array for optical CNNs. Optical delay lines replace electronics to execute data processing, which can reduce the scale of the input modulator array. The adoption of wavelength-division multiplexing enables a single group of optical delay lines to simultaneously process multiple input data, reducing the system complexity. The optical patching scheme provides a new solution to the problem of data input, which is challenging and concerned with the field of ONNs.

© 2020 Optical Society of America

High-accuracy automatic target recognition scheme based on a photonic analog-to-digital converter and a convolutional neural network

Jun Wan, Shaofu Xu, and Weiwen Zou
Opt. Lett. 45(24) 6855-6858 (2020)

Inverse design of plasmonic metasurfaces by convolutional neural network

Ronghui Lin, Yanfen Zhai, Chenxin Xiong, and Xiaohang Li
Opt. Lett. 45(6) 1362-1365 (2020)

Unveil the time delay signature of optical chaos systems with a convolutional neural network

Yetao Chen, Ronghuan Xin, Mengfan Cheng, Xiaojing Gao, Shanshan Li, Weidong Shao, Lei Deng, Minming Zhang, Songnian Fu, and Deming Liu
Opt. Express 28(10) 15221-15231 (2020)

Optical processor for a binarized neural network

Long Huang and Jianping Yao
Opt. Lett. 47(15) 3892-3895 (2022)

Generalized optical signal-to-noise ratio monitoring using a convolutional neural network for digital coherent receivers

Hyung Joon Cho
Opt. Lett. 48(7) 1798-1801 (2023)