Decision-making and control with diffractive optical networks  

作　　者：Jumin Qiu Shuyuan Xiao Lujun Huang Andrey Miroshnichenko Dejian Zhang Tingting Liu Tianbao Yu 

机构地区：[1]Nanchang University,School of Physics and Materials Science,Nanchang,China [2]Nanchang University,School of Information Engineering,Nanchang,China [3]Nanchang University,Institute for Advanced Study,Nanchang,China [4]East China Normal University,School of Physics and Electronic Science,Shanghai,China [5]University of New South Wales Canberra,School of Physics and Electronic Science,Canberra,Australia

出　　处：《Advanced Photonics Nexus》2024年第4期36-46,共11页先进光子学通讯（英文）

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.12064025,12264028,12364045,and 12304420);the Natural Science Foundation of Jiangxi Province(Grant Nos.20212ACB202006,20232BAB201040,and 20232BAB211025);the Shanghai Pujiang Program(Grant No.22PJ1402900);the Australian Research Council Discovery Project(Grant No.DP200101353);the Interdisciplinary Innovation Fund of Nanchang University(Grant No.2019-9166-27060003);the China Scholarship Council(Grant No.202008420045).

摘　　要：The ultimate goal of artificial intelligence(AI)is to mimic the human brain to perform decision-making and control directly from high-dimensional sensory input.Diffractive optical networks(DONs)provide a promising solution for implementing AI with high speed and low power-consumption.Most reported DONs focus on tasks that do not involve environmental interaction,such as object recognition and image classification.By contrast,the networks capable of decision-making and control have not been developed.Here,we propose using deep reinforcement learning to implement DONs that imitate human-level decisionmaking and control capability.Such networks,which take advantage of a residual architecture,allow finding optimal control policies through interaction with the environment and can be readily implemented with existing optical devices.The superior performance is verified using three types of classic games:tic-tac-toe,Super Mario Bros.,and Car Racing.Finally,we present an experimental demonstration of playing tic-tac-toe using the network based on a spatial light modulator.Our work represents a solid step forward in advancing DONs,which promises a fundamental shift from simple recognition or classification tasks to the high-level sensory capability of AI.It may find exciting applications in autonomous driving,intelligent robots,and intelligent manufacturing.

关 键 词：diffractive optical networks optical computing deep learning reinforcement learning 

分 类 号：TN9[电子电信—信息与通信工程]