Compelling evidence suggests that the interaction between electromagnetic metasurfaces and deep learning gives rise to the proliferation of intelligent metasurfaces in the past decade. In general, deep learning offers a transformative force to reform the design and working style of metasurfaces. A majority of the inverse-design literature announce that, given a user-defined input, the pre-trained deep learning models can quickly output the metasurface candidates with high fidelity. However, they largely ignore an important fact, that is, the practical input is always semi-known. In this work, we introduce a generation-elimination network that is robust to semi-known input and information pollution. The network is composed of a generative network to generate a number of possible answers and then a discriminative network to eliminate suboptimal answers. We benchmark the feasibility via two scenes, the on-demand metasurface design of the reflection spectra and the far-field pattern. In the microwave experiment, we fabricated and measured the reconfigurable metasurfaces to automatically meet the semi-known beam steering requirement that widely exist in wireless communication. Our work for the first time answers the question of how to cope with semi-known input, which is ubiquitous in a panoply of real-world applications, such as imaging, sensing, and communication across noisy environment.
10. Wang, Zhihao, Jian Chen, and Steven C. H. Hoi, "Deep learning for image super-resolution: A survey,", Vol. 43, 3365-3387, 2021.
doi:10.1109/TPAMI.2020.2982166
2. Purwins, Hendrik, Bo Li, Tuomas Virtanen, Jan Schlueter, Shuo-Yiin Chang, and Tara Sainath, "Deep learning for audio signal processing,", Vol. 13, 206-219, 2019.
doi:10.1109/JSTSP.2019.2908700
1. Qian, Chao, Yi Yang, Yifei Hua, Chan Wang, Xiao Lin, Tong Cai, Dexin Ye, Erping Li, Ido Kaminer, and Hongsheng Chen, "Breaking the fundamental scattering limit with gain metasurfaces,", Vol. 13, 4383, 2022.
doi:10.1038/s41467-022-32067-9
47. Cai, Tong, Bin Zheng, Jing Lou, Lian Shen, Yihao Yang, Shiwei Tang, Erping Li, Chao Qian, and Hongsheng Chen, "Experimental realization of a superdispersion-enabled ultrabroadband terahertz cloak,", Vol. 34, 2205053, 2022.
doi:10.1002/adma.202205053
1. Jia, Yuetian, Chao Qian, Zhixiang Fan, Tong Cai, Er-Ping Li, and Hongsheng Chen, "A knowledge-inherited learning for intelligent metasurface design and assembly,", Vol. 12, 82, 2023.
doi:10.1038/s41377-023-01131-4
He, Qiong, Shulin Sun, and Lei Zhou, "Tunable/Reconfigurable metasurfaces: physics and applications,", Vol. 2019, 1849272, 2019.
22. Huang, Cheng, Changlei Zhang, Jianing Yang, Bo Sun, Bo Zhao, and Xiangang Luo, "Reconfigurable metasurface for multifunctional control of electromagnetic waves,", Vol. 5, 1700485, 2017.
doi:10.1002/adom.201700485
1. Chen, Jieting, Chao Qian, Jie Zhang, Yuetian Jia, and Hongsheng Chen, "Correlating metasurface spectra with a generation-elimination framework,", Vol. 14, 4872, 2023.
doi:10.1038/s41467-023-40619-w
22. Wang, Zhedong, Min Chen, Chao Qian, Zhixiang Fan, Huaping Wang, and Hongsheng Chen, "Reconfigurable matrix multiplier with on-site reinforcement learning,", Vol. 47, 5897-5900, 2022.
doi:10.1364/OL.472729
5. Zhang, Jie, Chao Qian, Jieting Chen, Bei Wu, and Hongsheng Chen, "Uncertainty qualification for metasurface design with amendatory bayesian network,", Vol. 17, 2200807, 2023.
doi:10.1002/lpor.202200807
Khatib, Omar, Simiao Ren, Jordan Malof, and Willie J. Padilla, "Deep learning the electromagnetic properties of metamaterials - A comprehensive review,", Vol. 31, 2101748, 2021.
doi:10.1002/adfm.202101748
Ramprasad, Rampi, Rohit Batra, Ghanshyam Pilania, Arun Mannodi-Kanakkithodi, and Chiho Kim, "Machine learning in materials informatics: Recent applications and prospects,", Vol. 3, 54, 2017.
doi:10.1038/s41524-017-0056-5
19. Jia, Yuetian, Chao Qian, Zhixiang Fan, Yinzhang Ding, Zhedong Wang, Dengpan Wang, Er-Ping Li, Bin Zheng, Tong Cai, and Hongsheng Chen, "In situ customized illusion enabled by global metasurface reconstruction,", Vol. 32, 2109331, 2022.
doi:10.1002/adfm.202109331
Fan, Z., et al., "Transfer-learning-assisted inverse metasurface design with 30% data savings,", Vol. 18, 024022, 2022.
doi:10.1103/PhysRevApplied.18.024022
27. Fan, Zhixiang, Chao Qian, Yuetian Jia, Zhedong Wang, Yinzhang Ding, Dengpan Wang, Longwei Tian, Erping Li, Tong Cai, Bin Zheng, Ido Kaminer, and Hongsheng Chen, "Homeostatic neuro-metasurfaces for dynamic wireless channel management,", Vol. 8, eabn7905, 2022.
doi:10.1126/sciadv.abn7905
51. Gao, Li, Xiaozhong Li, Dianjing Liu, Lianhui Wang, and Zongfu Yu, "A bidirectional deep neural network for accurate silicon color design,", Vol. 31, 1905467, 2019.
doi:10.1002/adma.201905467
1. Qian, Chao, Zhedong Wang, Haoliang Qian, Tong Cai, Bin Zheng, Xiao Lin, Yichen Shen, Ido Kaminer, Erping Li, and Hongsheng Chen, "Dynamic recognition and mirage using neuro-metamaterials,", Vol. 13, 2694, 2022.
doi:10.1038/s41467-022-30377-6
8. Jiang, Jiaqi and Jonathan A. Fan, "Global optimization of dielectric metasurfaces using a physics-driven neural network,", Vol. 19, 5366-5372, 2019.
doi:10.1021/acs.nanolett.9b01857
1. Wiecha, Peter R. and Otto L. Muskens, "Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures,", Vol. 20, 329-338, 2020.
doi:10.1021/acs.nanolett.9b03971
6. Qian, Chao, Bin Zheng, Yichen Shen, Li Jing, Erping Li, Lian Shen, and Hongsheng Chen, "Deep-learning-enabled self-adaptive microwave cloak without human intervention,", Vol. 14, 383, 2020.
doi:10.1038/s41566-020-0604-2
9. Wang, Zhedong, Chao Qian, Tong Cai, Longwei Tian, Zhixiang Fan, Jian Liu, Yichen Shen, Li Jing, Jianming Jin, Er-Ping Li, Bin Zheng, and Hongsheng Chen, "Demonstration of spider-eyes-like intelligent antennas for dynamically perceiving incoming waves,", Vol. 3, 2100066, 2021.
doi:10.1002/aisy.202100066
7601. Raccuglia, Paul, Katherine C. Elbert, Philip D. F. Adler, Casey Falk, Malia B. Wenny, Aurelio Mollo, Matthias Zeller, Sorelle A. Friedler, Joshua Schrier, and Alexander J. Norquist, "Machine-learning-assisted materials discovery using failed experiments,", Vol. 533, 73-76, 2016.
doi:10.1038/nature17439
1. Qian, Chao, Xiao Lin, Xiaobin Lin, Jian Xu, Yang Sun, Erping Li, Baile Zhang, and Hongsheng Chen, "Performing optical logic operations by a diffractive neural network,", Vol. 9, 59, 2020.
doi:10.1038/s41377-020-0303-2
17. Zhang, Jie, Chao Qian, Zhixiang Fan, Jieting Chen, Erping Li, Jianming Jin, and Hongsheng Chen, "Heterogeneous transfer-learning-enabled diverse metasurface design,", Vol. 10, 2200748, 2022.
doi:10.1002/adom.202200748
7. Wu, Nanxuan, Yuetian Jia, Chao Qian, and Hongsheng Chen, "Pushing the limits of metasurface cloak using global inverse design,", Vol. 11, 2202130, 2023.
doi:10.1002/adom.202202130
7. Zhu, Xiaoyue, Chao Qian, Yuetian Jia, Jieting Chen, Yuan Fang, Zhixiang Fan, Jie Zhang, Dongdong Li, Reza Abdi-Ghaleh, and Hongsheng Chen, "Realization of index modulation with intelligent spatiotemporal metasurfaces,", Vol. 5, 2300065, 2023.
doi:10.1002/aisy.202300065
Kingma, D. P. and M. Welling, Auto-encoding variational bayes, 2014.
Sohn, Kihyuk, Xinchen Yan, and Honglak Lee, Learning structured output representation using deep conditional generative models, Advances in Neural Information Processing Systems (nips 2015), Vol. 28, Montreal, Canada, 2015.
18. Qian, Chao and Hongsheng Chen, "A perspective on the next generation of invisibility cloaks-intelligent cloaks,", Vol. 118, 180501, 2021.
doi:10.1063/5.0049748
5. Zhen, Zheng, Chao Qian, Yuetian Jia, Zhixiang Fan, Ran Hao, Tong Cai, Bin Zheng, Hongsheng Chen, and Erping Li, "Realizing transmitted metasurface cloak by a tandem neural network,", Vol. 9, B229-B235, 2021.
doi:10.1364/PRJ.418445
Wu, Q. and R. Zhang, "Intelligent reflecting surface enhanced wireless network via joint active and passive beamforming,", Vol. 18, 5394-5409, 2019.
doi:10.1109/TWC.2019.2936025
5. Basar, Ertugrul, "Reconfigurable intelligent surface-based index modulation: A new beyond MIMO paradigm for 6G,", Vol. 68, 3187-3196, 2020.
doi:10.1109/TCOMM.2020.2971486
Hu, Q., et al., "An intelligent programmable omni-metasurface,", Vol. 16, 2100718, 2022.
doi:10.1002/lpor.202100718
1. Lu, Huan, Jiwei Zhao, Bin Zheng, Chao Qian, Tong Cai, Erping Li, and Hongsheng Chen, "Eye accommodation-inspired neuro-metasurface focusing,", Vol. 14, 2023.
Zhang, K., et al., "Ultrasensitive self-driven terahertz photodetectors based on low-energy type-II dirac fermions and related van der Waals heterojunctions,", Vol. 19, 2205329, 2023.
doi:10.1002/smll.202205329
Hu, Z., et al., "Terahertz nonlinear hall rectifiers based on spin-polarized topological electronic states in 1T-CoTe2,", Vol. 35, 2209557, 2023.
doi:10.1002/adma.202209557
12. Rizza, Carlo, Debasis Dutta, Barun Ghosh, Francesca Alessandro, Chia-Nung Kuo, Chin Shan Lue, Lorenzo S. Caputi, Arun Bansil, Vincenzo Galdi, Amit Agarwal, Antonio Politano, and Anna Cupolillo, "Extreme optical anisotropy in the type-II dirac semimetal NiTe2 for applications to nanophotonics,", Vol. 5, 18531-18536, 2022.
doi:10.1021/acsanm.2c04340
Daws, Sawsan, Parth Kotak, Chia-Nung Kuo, Chin Shan Lue, Antonio Politano, and Caterina Lamuta, "Platinum diselenide PtSe2: An ambient-stable material for flexible electronics,", Vol. 283, 115824, 2022.
52. Vobornik, Ivana, Anan Bari Sarkar, Libo Zhang, Danil W. Boukhvalov, Barun Ghosh, Lesia Piliai, Chia-Nung Kuo, Debashis Mondal, Jun Fujii, Chin Shan Lue, Mykhailo Vorokhta, Huaizhong Xing, Lin Wang, Amit Agarwal, and Antonio Politano, "Kitkaite nitese, an ambient-stable layered dirac semimetal with low-energy type-ii fermions with application capabilities in spintronics and optoelectronics,", Vol. 31, 2106101, 2021.
doi:10.1002/adfm.202106101
Faenzi, M., et al., "Metasurface antennas: New models, applications and realizations,", Vol. 9, 10178, 2019.
doi:10.1038/s41598-019-46522-z
Badawe, M. E., T. S. Almoneef, and O. M. Ramahi, "A true metasurface antenna,", Vol. 6, 19268, 2016.
doi:10.1038/srep19268
Tan, Q., C. Qian, T. Cai, B. Zheng, and H. Chen, "Solving multivariable equations with tandem metamaterial kernels,", Vol. 175, 139-147, 2022.
doi:10.2528/PIER22060601
Shou, Y., Y. Feng, Y. Zhang, H. Chen, and H. Qian, "Deep learning approach based optical edge detection using ENZ layers,", Vol. 175, 81-89, 2022.
doi:10.2528/PIER22061403
Xie, H., T. Hu, Z. Wang, Y. Yang, X. Hu, W. Qi, and H. Liu, "A physics-based HIE-FDTD method for electromagnetic modeling of multi-band frequency selective surface,", Vol. 173, 129-140, 2022.
doi:10.2528/PIER22012103
, "test,".
doi:10.2528/PIER22012103
Submit
