Photonic convolution accelerator based on a hybrid integrated multi-wavelength laser array by photonic wire bonding for real-time image classification
Yuxin Ma, Kaifei Tang, Jun Kun Lu, Zhenxing Sun, Yao Lu, Yujiang Wang, zhenzhen Xu, Mi Li, Xin Wang, Rulei Xiao, Xin Yu, Jiahui Liu, Xiang Ji, Wei Jiang, Yuechun Shi, Xiangfei Chen · Optics Letters · 2024
We propose and experimentally demonstrate a compact and efficient photonic convolution accelerator based on a hybrid integrated multi-wavelength DFB laser array by photonic wire bonding. The photonic convolution accelerator operates at 60.12 GOPS for one 3 × 3 kernel with a convolution window vertical sliding stride of 1 and generates 500 images of real-time image classification. Furthermore, real-time image classification on the MNIST database of handwritten digits with a prediction accuracy of 93.86% is achieved. This work provides a novel, to the best of our knowledge, compact hybrid integration platform to realize the optical convolutional neural networks.