End-to-End Diverse Metasurface Design and Evaluation Using an Invertible Neural Network

被引:6
|
作者
Wang, Yunxiang [1 ]
Yang, Ziyuan [2 ]
Hu, Pan [1 ]
Hossain, Sushmit [1 ]
Liu, Zerui [1 ]
Ou, Tse-Hsien [1 ]
Ye, Jiacheng [1 ]
Wu, Wei [1 ]
机构
[1] Univ Southern Calif, Ming Hsieh Dept Elect Engn, Los Angeles, CA 90089 USA
[2] Renmin Univ China, High Sch, CUIWEI Campus, Beijing 100086, Peoples R China
关键词
deep learning; invertible neural network; metasurface; metalens; holograms; INVERSE DESIGN; DEEP;
D O I
10.3390/nano13182561
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Employing deep learning models to design high-performance metasurfaces has garnered significant attention due to its potential benefits in terms of accuracy and efficiency. A deep learning-based metasurface design framework typically comprises a forward prediction path for predicting optical responses and a backward retrieval path for generating geometrical configurations. In the forward design path, a specific geometrical configuration corresponds to a unique optical response. However, in the inverse design path, a single performance metric can correspond to multiple potential designs. This one-to-many mapping poses a significant challenge for deep learning models and can potentially impede their performance. Although representing the inverse path as a probabilistic distribution is a widely adopted method for tackling this problem, accurately capturing the posterior distribution to encompass all potential solutions remains an ongoing challenge. Furthermore, in most pioneering works, the forward and backward paths are captured using separate models. However, the knowledge acquired from the forward path does not contribute to the training of the backward model. This separation of models adds complexity to the system and can hinder the overall efficiency and effectiveness of the design framework. Here, we utilized an invertible neural network (INN) to simultaneously model both the forward and inverse process. Unlike other frameworks, INN focuses on the forward process and implicitly captures a probabilistic model for the inverse process. Given a specific optical response, the INN enables the recovery of the complete posterior over the parameter space. This capability allows for the generation of novel designs that are not present in the training data. Through the integration of the INN with the angular spectrum method, we have developed an efficient and automated end-to-end metasurface design and evaluation framework. This novel approach eliminates the need for human intervention and significantly speeds up the design process. Utilizing this advanced framework, we have effectively designed high-efficiency metalenses and dual-polarization metasurface holograms. This approach extends beyond dielectric metasurface design, serving as a general method for modeling optical inverse design problems in diverse optical fields.
引用
收藏
页数:14
相关论文
共 50 条
  • [41] An end-to-end neural network for UUV autonomous collision avoidance
    Lin, Changjian
    Wang, Hongjian
    Li, Benyin
    Zhang, Honghan
    Yuan, Jianya
    OCEAN ENGINEERING, 2023, 289
  • [42] END-TO-END NEURAL NETWORK BASED AUTOMATED SPEECH SCORING
    Chen, Lei
    Tao, Jidong
    Ghaffarzadegan, Shabnam
    Qian, Yao
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 6234 - 6238
  • [43] End-to-end predictive intelligence diagnosis in brain tumor using lightweight neural network
    Ma, Linjuan
    Zhang, Fuquan
    APPLIED SOFT COMPUTING, 2021, 111
  • [44] Contextual Speech Recognition in End-to-End Neural Network Systems using Beam Search
    Williams, Ian
    Kannan, Anjuli
    Aleksci, Petar
    Rybach, David
    Sainath, Tara N.
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 2227 - 2231
  • [45] Building End-to-End Dialogue Systems Using Generative Hierarchical Neural Network Models
    Serban, Iulian V.
    Sordoni, Alessandro
    Bengio, Yoshua
    Courville, Aaron
    Pineau, Joelle
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 3776 - 3783
  • [46] End-to-end recognition of slab identification numbers using a deep convolutional neural network
    Lee, Sang Jun
    Yun, Jong Pil
    Koo, Gyogwon
    Kim, Sang Woo
    KNOWLEDGE-BASED SYSTEMS, 2017, 132 : 1 - 10
  • [47] An End-to-End Object Detection System in Indoor Environments Using Lightweight Neural Network
    Afif, Mouna
    Said, Yahia
    Ayachi, Riadh
    Hleili, Manel
    TRAITEMENT DU SIGNAL, 2024, 41 (05) : 2711 - 2719
  • [48] An End-to-End Lane-Keeping Approach Using Light Weighted Neural Network
    Xie, Renhao
    Huang, Hongcheng
    Chu, Pengzhi
    2022 34TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2022, : 4141 - 4144
  • [49] End-to-End Neural Network for Autonomous Steering using LiDAR Point Cloud Data
    Yi, Xianyong
    Ghazzai, Hakim
    Massoud, Yehia
    2022 IEEE 65TH INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS 2022), 2022,
  • [50] End-to-End Spiking Neural Network for Speech Recognition Using Resonating Input Neurons
    Auge, Daniel
    Hille, Julian
    Kreutz, Felix
    Mueller, Etienne
    Knoll, Alois
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2021, PT V, 2021, 12895 : 245 - 256