Optical Neural Network Architecture for Deep Learning with Temporal Synthetic Dimension  

作　　者：彭擘 颜硕 成大立 俞丹英 刘展维 Vladislav V.Yakovlev 袁璐琦 陈险峰 Bo Peng;Shuo Yan;Dali Cheng;Danying Yu;Zhanwei Liu;Vladislav V.Yakovlev;Luqi Yuan;Xianfeng Chen(State Key Laboratory of Advanced Optical Communication Systems and Networks,School of Physics and Astronomy,Shanghai Jiao Tong University,Shanghai 200240,China;Ginzton Laboratory and Department of Electrical Engineering,Stanford University,Stanford,CA 49305,USA;Texas A&M University,College Station,Texas 77843,USA;Shanghai Research Center for Quantum Sciences,Shanghai 201315,China;Collaborative Innovation Center of Light Manipulation and Applications,Shandong Normal University,Jinan 250358,China)

机构地区：[1]State Key Laboratory of Advanced Optical Communication Systems and Networks,School of Physics and Astronomy,Shanghai Jiao Tong University,Shanghai 200240,China [2]Ginzton Laboratory and Department of Electrical Engineering,Stanford University,Stanford,CA 49305,USA [3]Texas A&M University,College Station,Texas 77843,USA [4]Shanghai Research Center for Quantum Sciences,Shanghai 201315,China [5]Collaborative Innovation Center of Light Manipulation and Applications,Shandong Normal University,Jinan 250358,China

出　　处：《Chinese Physics Letters》2023年第3期13-18,共6页中国物理快报（英文版）

基　　金：the National Natural Science Foundation of China(Grant Nos.12122407,11974245,and 12192252);the Shanghai Municipal Science and Technology Major Project(Grant No.2019SHZDZX01-ZX06);partial funding from NSF(Grant Nos.DBI-1455671,ECCS-1509268,and CMMI-1826078);AFOSR(Grant Nos.FA9550-15-1-0517,FA9550-18-1-0141,FA9550-201-0366,and FA9550-20-1-0367);DOD Army Medical Research(Grant No.W81XWH2010777);NIH(Grant Nos.1R01GM127696-01 and 1R21GM142107-01);the Cancer Prevention and Research Institute of Texas(Grant No.RP180588);the sponsorship from Yangyang Development Fund;the support from the Program for Professor of Special Appointment(Eastern Scholar)at Shanghai Institutions of Higher Learning。

摘　　要：The physical concept of synthetic dimensions has recently been introduced into optics.The fundamental physics and applications are not yet fully understood,and this report explores an approach to optical neural networks using synthetic dimension in time domain,by theoretically proposing to utilize a single resonator network,where the arrival times of optical pulses are interconnected to construct a temporal synthetic dimension.The set of pulses in each roundtrip therefore provides the sites in each layer in the optical neural network,and can be linearly transformed with splitters and delay lines,including the phase modulators,when pulses circulate inside the network.Such linear transformation can be arbitrarily controlled by applied modulation phases,which serve as the building block of the neural network together with a nonlinear component for pulses.We validate the functionality of the proposed optical neural network for the deep learning purpose with examples handwritten digit recognition and optical pulse train distribution classification problems.This proof of principle computational work explores the new concept of developing a photonics-based machine learning in a single ring network using synthetic dimensions,which allows flexibility and easiness of reconfiguration with complex functionality in achieving desired optical tasks.

关 键 词：NETWORK RESONATOR NEURAL 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] O439[自动化与计算机技术—控制科学与工程]