Abstract

We experimentally establish a 3 × 3 cross-shaped micro-ring resonator (MRR) array-based photonic multiplexing architecture relying on silicon photonics to achieve parallel edge extraction operations in images for photonic convolution neural networks. The main mathematical operations involved are convolution. Precisely, a faster convolutional calculation speed of up to four times is achieved by extracting four feature maps simultaneously with the same photonic hardware’s structure and power consumption, where a maximum computility of 0.742 TOPS at an energy cost of 48.6 mW and a convolution accuracy of 95.1% is achieved in an MRR array chip. In particular, our experimental results reveal that this system using parallel edge extraction operators instead of universal operators can improve the imaging recognition accuracy for CIFAR-10 dataset by 6.2% within the same computing time, reaching a maximum of 78.7%. This work presents high scalability and efficiency of parallel edge extraction chips, furnishing a novel, to the best of our knowledge, approach to boost photonic computing speed.

© 2024 Optica Publishing Group

On-chip photonic convolution by phase-change in-memory computing cells with quasi-continuous tuning

Jigeng Sun, Shaolin Zhou, Ziyang Ye, Bo Hu, and Yi Zou
Opt. Express 32(9) 14994-15007 (2024)

Dual-convolutional neural network-enhanced strain estimation method for optical coherence elastography

Yulei Bai, Zhanhua Zhang, Zhaoshui He, Shengli Xie, and Bo Dong
Opt. Lett. 49(3) 438-441 (2024)

Iterative eigensolver using fixed-point photonic primitive

Andrew B. Klein, Zheyuan Zhu, Dewan Saiham, Guifang Li, and Shuo S. Pang
Opt. Lett. 49(2) 194-197 (2024)

Ultrahigh-speed phase demodulation of a Fabry–Perot sensor based on fiber array parallel spectral detection

Chenxi Li, Hongchao Qi, Xiao Han, Xinyu Zhao, Yajie Zhang, Jiayu Huang, Wei Peng, and Ke Chen
Opt. Lett. 49(3) 714-717 (2024)

FSMN-Net: a free space matching network based on manifold convolution for optical molecular tomography

Shuangchen Li, Beilei Wang, Jingjing Yu, Xuelei He, Hongbo Guo, and Xiaowei He
Opt. Lett. 49(5) 1161-1164 (2024)