Abstract

We propose and experimentally demonstrate a simple and energy-efficient photonic convolutional accelerator based on a monolithically integrated multi-wavelength distributed feedback semiconductor laser using the superimposed sampled Bragg grating structure. The photonic convolutional accelerator operates at 44.48 GOPS for one 2 × 2 kernel with a convolutional window vertical sliding stride of 2 and generates 100 images of real-time recognition. Furthermore, a real-time recognition task on the MNIST database of handwritten digits with a prediction accuracy of 84% is achieved. This work provides a compact and low-cost way to realize photonic convolutional neural networks.

© 2022 Optica Publishing Group

Photonics-enabled spiking timing-dependent convolutional neural network for real-time image classification

Xiangyan Meng, Nuannuan Shi, Difei Shi, Wei Li, and Ming Li
Opt. Express 30(10) 16217-16228 (2022)

Programmable low-threshold optical nonlinear activation functions for photonic neural networks

Ying Huang, Weiping Wang, Lei Qiao, Xiaoyan Hu, and Tao Chu
Opt. Lett. 47(7) 1810-1813 (2022)

Monolithic multi-wavelength lasing from multi-sized microdisk lasers

Wai Yuen Fu, Yuk Fai Cheung, and Hoi Wai Choi
Opt. Lett. 47(24) 6397-6400 (2022)

Experimental demonstration of a multi-wavelength distributed feedback semiconductor laser array with an equivalent chirped grating profile based on the equivalent chirp technology

Wangzhe Li, Xia Zhang, and Jianping Yao
Opt. Express 21(17) 19966-19971 (2013)

Experimental demonstration of tomography-based quantum key distribution

Min Wei, Chun-Hui Zhang, Jian Li, Jia-Li Zhu, and Qin Wang
Opt. Lett. 47(23) 6285-6288 (2022)