Photonic Integrated Neuro-Synaptic Core for Convolutional Spiking Neural Network
Abstract
Neuromorphic photonic computing has emerged as a competitive computing paradigm to overcome the bottlenecks of the von-Neumann architecture. Linear weighting and nonlinear spiking activation are two fundamental functions of a photonic spiking neural network (PSNN). However, they are separately implemented with different photonic materials and devices, hindering the large-scale integration of PSNN. Here, we propose, fabricate and experimentally demonstrate a photonic neuro-synaptic chip enabling the simultaneous implementation of linear weighting and nonlinear spiking activation based on a distributed feedback (DFB) laser with a saturable absorber (DFB-SA). A prototypical system is experimentally constructed to demonstrate the parallel weighted function and nonlinear spike activation. Furthermore, a four-channel DFB-SA array is fabricated for realizing matrix convolution of a spiking convolutional neural network, achieving a recognition accuracy of 87% for the MNIST dataset. The fabricated neuro-synaptic chip offers a fundamental building block to construct the large-scale integrated PSNN chip.
Keywords
Cite
@article{arxiv.2306.02724,
title = {Photonic Integrated Neuro-Synaptic Core for Convolutional Spiking Neural Network},
author = {Shuiying Xiang and Yuechun Shi and Yahui Zhang and Xingxing Guo and Ling Zheng and Yanan Han and Yuna Zhang and Ziwei Song and Dianzhuang Zheng and Tao Zhang and Hailing Wang and Xiaojun Zhu and Xiangfei Chen and Min Qiu and Yichen Shen and Wanhua Zheng and Yue Hao},
journal= {arXiv preprint arXiv:2306.02724},
year = {2023}
}