Thin-film neural networks for optical inverse problem

作     者：Lingjie Fan Ang Chen Tongyu Li Jiao Chu Yang Tang Jiajun Wang Maoxiong Zhao Tangyao Shen Minjia Zheng Fang Guan Haiwei Yin Lei Shi Jian Zi 

作者机构：State Key Laboratory of Surface PhysicsKey Laboratory of Micro-and Nano-Photonic Structures(Ministry of Education)and Department of PhysicsFudan UniversityShanghai 200433China Shanghai Engineering Research Center of Optical Metrology for Nano-fabrication(SERCOM)Shanghai 200433China Institute for Nanoelectronic devices and Quantum computingFudan UniversityShanghai 200438China Collaborative Innovation Center of Advanced MicrosstructuresNanjing UniversityNanjing 210093China 

出 版 物：《Light(Advanced Manufacturing)》 (光（先进制造）（英文）)

年 卷 期：2021年第2卷第4期

页      面：23-30页

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 07[理学] 070205[理学-凝聚态物理] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 080502[工学-材料学] 0702[理学-物理学] 

基　　金：This work was supported by the China National Key Basic Research Program(2018YFA0306201) the National Science Foundation of China(11774063,11727811,and 91963212) A.C.was supported by the Shanghai Rising-Star Program(20QR1402200) L.S.was further supported by the Science and Technology Commission of Shanghai Municipality(19XD143600,2019SHZDZX01,19DZ2253000,20501110500) 

主　　题：method inverse film 

摘      要：The thin-film optical inverse problem has attracted a great deal of attention in science and industry,and is widely applied to optical ***,as the number of layers increases,the time it takes to extract the parameters of thin films drastically ***,we introduce the idea of exploiting the structural similarity of all-optical neural networks and applied it to the optical inverse *** propose thin-film neural networks(TFNNs)to efficiently adjust all the parameters of multilayer thin *** test the performance of TFNNs,we implemented a TFNN algorithm,and a reflectometer at normal incidence was *** on multilayer thin films with 232 layers,it is shown that TFNNs can reduce the time consumed by parameter extraction,which barely increased with the number of layers compared with the conventional *** were also used to design multilayer thin films to mimic the optical response of three types of cone cells in the human *** light passing through these multilayer thin films was then recorded as a colored photo.