Abstract

Integrated diffractive optical neural networks (DONNs) have significant potential for complex machine learning tasks with high speed and ultralow energy consumption. However, the on-chip implementation of a high-performance optical neural network is limited by input dimensions. In contrast to existing photonic neural networks, a space-time interleaving technology based on arrayed waveguides is designed to realize an on-chip DONN with high-speed, high-dimensional, and all-optical input signal modulation. To demonstrate the performance of the on-chip DONN with high-speed space-time interleaving modulation, an on-chip DONN with a designed footprint of 0.0945 mm² is proposed to resolve the vowel recognition task, reaching a computation speed of about 1.4×10¹³ operations per second and yielding an accuracy of 98.3% in numerical calculation. In addition, the function of the specially designed arrayed waveguides for realizing parallel signal inputs using space-time conversion has been verified experimentally. This method can realize the on-chip DONN with higher input dimension and lower energy consumption.

© 2023 Chinese Laser Press

On-chip photonic diffractive optical neural network based on a spatial domain electromagnetic propagation model

Tingzhao Fu, Yubin Zang, Honghao Huang, Zhenmin Du, Chengyang Hu, Minghua Chen, Sigang Yang, and Hongwei Chen
Opt. Express 29(20) 31924-31940 (2021)

C-DONN: compact diffractive optical neural network with deep learning regression

Wencan Liu, Tingzhao Fu, Yuyao Huang, Run Sun, Sigang Yang, and Hongwei Chen
Opt. Express 31(13) 22127-22143 (2023)

Integrated photonic neural network based on silicon metalines

Sanaz Zarei, Mahmood-reza Marzban, and Amin Khavasi
Opt. Express 28(24) 36668-36684 (2020)

Space–time-sharing optical neural network

Francis T. S. Yu, Xiangyang Yang, and Taiwei Lu
Opt. Lett. 16(4) 247-249 (1991)

Parity–time symmetric optical neural networks

Haoqin Deng and Mercedeh Khajavikhan
Optica 8(10) 1328-1333 (2021)