PubCard - Photonic integrated neuro-synaptic core for convolutional spiking neural network

(Peer-Reviewed) Photonic integrated neuro-synaptic core for convolutional spiking neural network

Shuiying Xiang 项水英 ¹, Yuechun Shi 施跃春 ², Yahui Zhang 张雅慧 ¹, Xingxing Guo 郭星星 ¹, Ling Zheng 郑凌 ³, Yanan Han 韩亚楠 ¹, Yuna Zhang 张钰娜 ¹, Ziwei Song 宋紫薇 ¹, Dianzhuang Zheng 郑殿壮 ¹, Tao Zhang 张涛 ¹, Hailing Wang 王海玲 ⁴, Xiaojun Zhu 朱晓军 ⁵, Xiangfei Chen 陈向飞 ⁶, Min Qiu 仇旻 ⁷, Yichen Shen 沈亦晨 ⁸, Wanhua Zheng 郑婉华 ⁴, Yue Hao 郝跃 ¹

¹ State Key Laboratory of Integrated Service Networks, State Key Discipline Laboratory of Wide Bandgap Semiconductor Technology, Xidian University, Xi'an 710071, China
中国西安西安电子科技大学综合业务网理论及关键技术国家重点实验室宽带隙半导体技术国家重点学科实验室
² Yongjiang laboratory, No. 1792 Cihai South Road, Ningbo 315202, China
中国宁波甬江实验室
³ The School of Communications and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an 710121, China
中国西安西安邮电大学通信与信息工程学院
⁴ Laboratory of Solid-State Optoelectronics Information Technology, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China
中国北京中国科学院半导体研究所固态光电信息技术研究室
⁵ School of Information Science and Technology, Nantong University, Nantong 226019, China
中国南通南通大学信息科学技术学院
⁶ The College of Engineering and Applied Sciences, Nanjing University, Nanjing 210023, China
中国南京南京大学现代工程与应用科学学院
⁷ Key Laboratory of 3D Micro/Nano Fabrication and Characterization of Zhejiang Province, School of Engineering, Westlake University, Hangzhou 310024, China
中国杭州西湖大学工学院浙江省3D微纳加工和表征研究重点实验室
⁸ Lightelligence Group, Hangzhou 311121, China
中国杭州曦智科技

Opto-Electronic Advances, 2023-11-15

https://doi.org/10.29026/oea.2023.230140

https://www.oejournal.org/article/doi/10.29026/oea.2023.230140

Abstract

Neuromorphic photonic computing has emerged as a competitive computing paradigm to overcome the bottlenecks of the von-Neumann architecture. Linear weighting and nonlinear spike 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 spike 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 laser 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.