E-mail Alert
RSS
| Citation: |
|
-
Abstract
In the recent years, a dramatic boost of the research is observed at the junction of photonics, machine learning and artificial intelligence. A new methodology can be applied to the description of a variety of photonic systems including optical waveguides, nanoantennas, and metasurfaces. These novel approaches underpin the fundamental principles of light-matter interaction developed for a smart design of intelligent photonic devices. Artificial intelligence and machine learning penetrate rapidly into the fundamental physics of light, and they provide effective tools for the study of the field of metaphotonics driven by optically induced electric and magnetic resonances. Here we overview the evaluation of metaphotonics induced by artificial intelligence and present a summary of the concepts of machine learning with some specific examples developed and demonstrated for metasystems and metasurfaces.-
Keywords:
- metaphotonics /
- machine learning /
- artificial intelligence
-
-
References
[1] Radovic A, Williams M, Rousseau D, Kagan M, Bonacorsi D et al. Machine learning at the energy and intensity frontiers of particle physics. Nature 560, 41–48 (2018). doi: 10.1038/s41586-018-0361-2 [2] Schmidt J, Marques MRG, Botti S, Marques MAL. Recent advances and applications of machine learning in solid-state materials science. Npj Comput Mater 5, 83 (2019). doi: 10.1038/s41524-019-0221-0 [3] Brown KA, Brittman S, Maccaferri N, Jariwala D, Celano U. Machine learning in nanoscience: big data at small scales. Nano Lett 20, 2–10 (2020). doi: 10.1021/acs.nanolett.9b04090 [4] Carrasquilla J. Machine learning for quantum matter. Adv Phys X 5, 1797528 (2020). [5] Bedolla E, Padierna LC, Castañeda-Priego R. Machine learning for condensed matter physics. J Phys Condens Matter 33, 053001 (2021). doi: 10.1088/1361-648X/abb895 [6] Campbell SD, Jenkins RP, O’Connor PJ, Werner D. The explosion of artificial intelligence in antennas and propagation: how deep learning is advancing our state of the art. IEEE Antennas Propag Mag 63, 16–27 (2021). doi: 10.1109/MAP.2020.3021433 [7] Koshelev K, Kivshar Y. Dielectric resonant metaphotonics. ACS Photonics 8, 102–112 (2021). [8] Zheludev NI, Kivshar YS. From metamaterials to metadevices. Nat Mater 11, 917–924 (2012). doi: 10.1038/nmat3431 [9] Kruk S, Kivshar Y. Functional meta-optics and nanophotonics governed by mie resonances. ACS Photonics 4, 2638–2649 (2017). doi: 10.1021/acsphotonics.7b01038 [10] Mohri M, Rostamizadeh A, Talwalkar A. Foundations of Machine Learning (MIT Press, Cambridge, 2018). [11] Mehta P, Bukov M, Wang CH, Day AGR, Richardson C et al. A high-bias, low-variance introduction to Machine Learning for physicists. Phys Rep 810, 1–124 (2019). doi: 10.1016/j.physrep.2019.03.001 [12] Roscher R, Bohn B, Duarte MF, Garcke J. Explainable machine learning for scientific insights and discoveries. IEEE Access 8, 42200–42216 (2020). doi: 10.1109/ACCESS.2020.2976199 [13] Tanaka A, Tomiya A, Hashimoto K. Deep Learning and Physics (Springer, Singapore, 2021);https://doi.org/10.1007/978-981-33-6108-9. [14] Miyanawala TP, Jaiman RK. An efficient deep learning technique for the navier-stokes equations: application to unsteady wake flow dynamics. ArXiv: 1710.09099 (2018). [15] Lucor D, Agrawal A, Sergent A. Physics-aware deep neural networks for surrogate modeling of turbulent natural convection. ArXiv: 2103.03565 (2021). [16] Lim J, Psaltis D. MaxwellNet: physics-driven deep neural network training based on Maxwell’s equations. ArXiv: 2107.06164 (2021). [17] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 521, 436–444 (2015). doi: 10.1038/nature14539 [18] Goodfellow I, Bengio Y, Courville A. Deep Learning (MIT Press, Cambridge, 2016). [19] Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw 2, 359–366 (1989). doi: 10.1016/0893-6080(89)90020-8 [20] Myung IJ. The importance of complexity in model selection. J Math Psychol 44, 190–204 (2000). doi: 10.1006/jmps.1999.1283 [21] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In Proceedings of the 3rd International Conference on Learning Representations (ICLR, 2015). [22] Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J et al. Language models are few-shot learners. In Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS, 2020). [23] van Oord A, Kalchbrenner N, Kavukcuoglu K. Pixel recurrent neural networks. In Proceedings of the 33rd International Conference on Machine Learning 1747–1756 (PMLR, 2016). [24] Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature 323, 533–536 (1986). doi: 10.1038/323533a0 [25] Sun F, Zheng B, Chen HS, Jiang W, Guo SW et al. Transformation optics: from classic theory and applications to its new branches. Laser Photonics Rev 11, 1700034 (2017). doi: 10.1002/lpor.201700034 [26] So S, Park N, Lee HJ, Rho J. New trends in nanophotonics. Nanophotonics 9, 983–985 (2020). doi: 10.1515/nanoph-2020-0170 [27] Chen ZG, Segev M. Highlighting photonics: looking into the next decade. eLight 1, 2 (2021). doi: 10.1186/s43593-021-00002-y [28] Li NN, Lai YH, Lam SH, Bai HY, Shao L et al. Directional control of light with nanoantennas. Adv Opt Mater 9, 2001081 (2021). doi: 10.1002/adom.202001081 [29] Rybin MV, Koshelev KL, Sadrieva ZF, Samusev KB, Bogdanov AA et al. High-Q supercavity modes in subwavelength dielectric resonators. Phys Rev Lett 119, 243901 (2017). doi: 10.1103/PhysRevLett.119.243901 [30] Kildishev AV, Boltasseva A, Shalaev VM. Planar photonics with metasurfaces. Science 339, 1232009 (2013). doi: 10.1126/science.1232009 [31] Lalanne P, Chavel P. Metalenses at visible wavelengths: past, present, perspectives. Laser Photonics Rev 11, 1600295 (2017). doi: 10.1002/lpor.201600295 [32] Hsiao HH, Chu CH, Tsai DP. Fundamentals and applications of metasurfaces. Small Methods 1, 1600064 (2017). doi: 10.1002/smtd.201600064 [33] Qiu CW, Zhang T, Hu GW, Kivshar Y. Quo vadis, metasurfaces. Nano Lett 21, 5461–5474 (2021). doi: 10.1021/acs.nanolett.1c00828 [34] Chen WT, Capasso F. Will flat optics appear in everyday life anytime soon. Appl Phys Lett 118, 100503 (2021). doi: 10.1063/5.0039885 [35] Peurifoy J, Shen YC, Jing L, Yang Y, Cano-Renteria F et al. Nanophotonic particle simulation and inverse design using artificial neural networks. Sci Adv 4, eaar4206 (2018). doi: 10.1126/sciadv.aar4206 [36] Hu BQ, Wu B, Tan D, Xu J, Xu J, Chen YT. Robust inverse-design of scattering spectrum in core-shell structure using modified denoising autoencoder neural network. Opt Express 27, 36276–36285 (2019). doi: 10.1364/OE.27.036276 [37] Qiu CK, Luo Z, Wu X, Yang HD, Huang B. Inverse design of multilayer nanoparticles using artificial neural networks and genetic algorithm. ArXiv: 2003.08356 (2020). [38] So S, Mun J, Rho J. Simultaneous inverse design of materials and structures via deep learning: demonstration of dipole resonance engineering using core–shell nanoparticles. ACS Appl Mater Interfaces 11, 24264–24268 (2019). doi: 10.1021/acsami.9b05857 [39] Qin FF, Zhang DS, Liu ZZ, Zhang Q, Xiao JJ. Designing metal-dielectric nanoantenna for unidirectional scattering via Bayesian optimization. Opt Express 27, 31075–31086 (2019). doi: 10.1364/OE.27.031075 [40] Wiecha PR, Muskens OL. Deep learning meets nanophotonics: a generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures. Nano Lett 20, 329–338 (2020). doi: 10.1021/acs.nanolett.9b03971 [41] Vahidzadeh E, Shankar K. Artificial neural network-based prediction of the optical properties of spherical core–shell plasmonic metastructures. Nanomaterials 11, 633 (2021). doi: 10.3390/nano11030633 [42] Cao ZL, Cui FP, Xian FL, Zhai CJ, Pei SX. A hybrid approach using machine learning and genetic algorithm to inverse modeling for single sphere scattering in a Gaussian light sheet. J Quant Spectrosc Radiat Transf 235, 180–186 (2019). doi: 10.1016/j.jqsrt.2019.07.002 [43] Li YZ, Wang YP, Qi ST, Ren Q, Kang L et al. Predicting scattering from complex nano-structures via deep learning. IEEE Access 8, 139983–139993 (2020). doi: 10.1109/ACCESS.2020.3012132 [44] Guo R, Lin ZC, Shan T, Song XQ, Li MK et al. Physics embedded deep neural network for solving full-wave inverse scattering problems. IEEE Trans Antennas Propag (2021); https://doi.org/10.1109/TAP.2021.3102135. [45] Lin ZC, Guo R, Li MK, Abubakar A, Zhao T et al. Low-frequency data prediction with iterative learning for highly nonlinear inverse scattering problems. IEEE Trans Microw Theory Tech 69, 4366–4376 (2021). doi: 10.1109/TMTT.2021.3098769 [46] Qie JR, Khoram E, Liu DJ, Zhou M, Gao L. Real-time deep learning design tool for far-field radiation profile. Photonics Res 9, B104–B108 (2021). doi: 10.1364/PRJ.413567 [47] Sheverdin A, Monticone F, Valagiannopoulos C. Photonic inverse design with neural networks: the case of invisibility in the visible. Phys Rev Appl 14, 024054 (2020). doi: 10.1103/PhysRevApplied.14.024054 [48] Luo J, Li X, Zhang XY, Guo JJ, Liu W et al. Deep-learning-enabled inverse engineering of multi-wavelength invisibility-to-superscattering switching with phase-change materials. Opt Express 29, 10527–10537 (2021). doi: 10.1364/OE.422119 [49] Blanchard-Dionne AP, Martin OJF. Successive training of a generative adversarial network for the design of an optical cloak. OSA Continuum 4, 87–95 (2021). doi: 10.1364/OSAC.413394 [50] Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng 22, 1345–1359 (2010). doi: 10.1109/TKDE.2009.191 [51] Zhuang FZ, Qi ZY, Duan KY, Xi DB, Zhu YC et al. A comprehensive survey on transfer learning. Proc IEEE 109, 43–76 (2021). doi: 10.1109/JPROC.2020.3004555 [52] Qu YR, Jing L, Shen YC, Qiu M, Soljačić M. Migrating knowledge between physical scenarios based on artificial neural networks. ACS Photonics 6, 1168–1174 (2019). doi: 10.1021/acsphotonics.8b01526 [53] Qiu CK, Wu X, Luo Z, Yang HD, He GN et al. Nanophotonic inverse design with deep neural networks based on knowledge transfer using imbalanced datasets. Opt Express 29, 28406–28415 (2021). doi: 10.1364/OE.435427 [54] Elzouka M, Yang C, Albert A, Lubner S, Prasher RS. Interpretable inverse design of particle spectral emissivity using machine learning. ArXiv: 2002.04223 (2020). [55] He J, He C, Zheng C, Wang Q, Ye J. Plasmonic nanoparticle simulations and inverse design using machine learning. Nanoscale 11, 17444–17459 (2019). doi: 10.1039/C9NR03450A [56] Wu QX, Li XZ, Jiang L, Xu X, Fang D et al. Deep neural network for designing near- and far-field properties in plasmonic antennas. Opt Mater Express 11, 1907–1917 (2021). doi: 10.1364/OME.428772 [57] Hassan SA. Artificial neural networks for the inverse design of nanoparticles with preferential nano-bio behaviors. J Chem Phys 153, 054102 (2020). doi: 10.1063/5.0013990 [58] Nelson MD, Di Vece M. Using a neural network to improve the optical absorption in halide perovskite layers containing core-shells silver nanoparticles. Nanomaterials 9, 437 (2019). doi: 10.3390/nano9030437 [59] Yeung C, Tsai JM, King B, Pham B, Ho D et al. Multiplexed supercell metasurface design and optimization with tandem residual networks. Nanophotonics 10, 1133–1143 (2021). doi: 10.1515/nanoph-2020-0549 [60] Zhu RC, Qiu TS, Wang JF, Sui S, Hao CL et al. Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning. Nat Commun 12, 2974 (2021). doi: 10.1038/s41467-021-23087-y [61] Malkiel I, Mrejen M, Wolf L, Suchowski H. Inverse design of unparametrized nanostructures by generating images from spectra. Opt Lett 46, 2087–2090 (2021). doi: 10.1364/OL.415553 [62] Xu D, Luo Y, Luo J, Pu MB, Zhang YX et al. Efficient design of a dielectric metasurface with transfer learning and genetic algorithm. Opt Mater Express 11, 1852–1862 (2021). doi: 10.1364/OME.427426 [63] Zhu DY, Liu ZC, Raju L, Kim AS, Cai WS. Building multifunctional metasystems via algorithmic construction. ACS Nano 15, 2318–2326 (2021). doi: 10.1021/acsnano.0c09424 [64] Zhelyeznyakov MV, Brunton S, Majumdar A. Deep learning to accelerate scatterer-to-field mapping for inverse design of dielectric metasurfaces. ACS Photonics 8, 481–488 (2021). [65] Colburn S, Majumdar A. Inverse design and flexible parameterization of meta-optics using algorithmic differentiation. Commun Phys 4, 65 (2021). doi: 10.1038/s42005-021-00568-6 [66] An SS, Zheng BW, Tang H, Shalaginov MY, Zhou L et al. Multifunctional metasurface design with a generative adversarial network. Adv Opt Mater 9, 2001433 (2021). doi: 10.1002/adom.202001433 [67] Han C, Zhang BF, Wang H, Ding JP. Metamaterial perfect absorber with morphology-engineered meta-atoms using deep learning. Opt Express 29, 19955–19963 (2021). doi: 10.1364/OE.427593 [68] So S, Yang Y, Lee T, Rho J. On-demand design of spectrally sensitive multiband absorbers using an artificial neural network. Photonics Res 9, B153–B158 (2021). doi: 10.1364/PRJ.415789 [69] Chen J, Ding W, Li XM, Xi X, Ye KP et al. Absorption and diffusion enabled ultrathin broadband metamaterial absorber designed by deep neural network and PSO. IEEE Antennas Wirel Propag Lett 20, 1993–1997 (2021). doi: 10.1109/LAWP.2021.3101703 [70] Sajedian I, Kim J, Rho J. Finding the optical properties of plasmonic structures by image processing using a combination of convolutional neural networks and recurrent neural networks. Microsyst Nanoeng 5, 27 (2019). doi: 10.1038/s41378-019-0069-y [71] Lin RH, Zhai YF, Xiong CX, Li XH. Inverse design of plasmonic metasurfaces by convolutional neural network. Opt Lett 45, 1362–1365 (2020). doi: 10.1364/OL.387404 [72] Deng Y, Ren SM, Fan KB, Malof JM, Padilla WJ. Neural-adjoint method for the inverse design of all-dielectric metasurfaces. Opt Express 29, 7526–7534 (2021). doi: 10.1364/OE.419138 [73] Badloe T, Kim I, Rho J. Biomimetic ultra-broadband perfect absorbers optimised with reinforcement learning. Phys Chem Chem Phys 22, 2337–2342 (2020). doi: 10.1039/C9CP05621A [74] Ghorbani F, Beyraghi S, Shabanpour J, Oraizi H, Soleimani H et al. Deep neural network-based automatic metasurface design with a wide frequency range. Sci Rep 11, 7102 (2021). doi: 10.1038/s41598-021-86588-2 [75] Ghorbani F, Shabanpour J, Beyraghi S, Soleimani H, Oraizi H et al. A deep learning approach for inverse design of the metasurface for dual-polarized waves. ArXiv: 2105.08508 (2021). [76] Koziel S, Abdullah M. Machine-learning-powered EM-based framework for efficient and reliable design of low scattering metasurfaces. IEEE Trans Microw Theory Tech 69, 2028–2041 (2021). doi: 10.1109/TMTT.2021.3061128 [77] Koziel S, Abdullah M, Szczepanski S. Design of high-performance scattering metasurfaces through optimization-based explicit RCS reduction. IEEE Access 9, 113077–113088 (2021). doi: 10.1109/ACCESS.2021.3104338 [78] Zandehshahvar M, Kiarashi Y, Zhu ML, Maleki H, Brown T et al. Manifold learning for knowledge discovery and intelligent inverse design of photonic nanostructures: breaking the geometric complexity. ArXiv: 2102.04454 (2021). [79] Wang HP, Li YB, Li H, Dong SY, Liu C et al. Deep learning designs of anisotropic metasurfaces in ultrawideband based on generative adversarial networks. Adv Intell Syst 2, 2000068 (2020). doi: 10.1002/aisy.202000068 [80] Naseri P, Pearson S, Wang ZZ, Hum SV. A combined machine-learning/optimization-based approach for inverse design of nonuniform bianisotropic metasurfaces. ArXiv: 2105.14133 (2021). [81] Huang W, Wei ZM, Tan BY, Yin S, Zhang WT. Inverse engineering of electromagnetically induced transparency in terahertz metamaterial via deep learning. J Phys D Appl Phys 54, 135102 (2021). doi: 10.1088/1361-6463/abd4a6 [82] Yuan L, Wang L, Yang XS, Huang H, Wang BZ. An efficient artificial neural network model for inverse design of metasurfaces. IEEE Antennas Wirel Propag Lett 20, 1013–1017 (2021). doi: 10.1109/LAWP.2021.3069713 [83] Zhang Z, Han D, Zhang LY, Wang XQ, Chen XF. Adaptively reverse design of terahertz metamaterial for electromagnetically induced transparency with generative adversarial network. J Appl Phys 130, 033101 (2021). doi: 10.1063/5.0054080 [84] Zhang J, Luo Y, Tao Z, You J. Graphic-processable deep neural network forthe efficient prediction of 2D diffractive chiral metamaterials. Appl Opt 60, 5691–5698 (2021). doi: 10.1364/AO.428581 [85] Ma W, Cheng F, Liu YM. Deep-learning-enabled on-demand design of chiral metamaterials. ACS Nano 12, 6326–6334 (2018). doi: 10.1021/acsnano.8b03569 [86] Li Y, Xu YJ, Jiang ML, Li BW, Han TY et al. Self-learning perfect optical chirality via a deep neural network. Phys Rev Lett 123, 213902 (2019). doi: 10.1103/PhysRevLett.123.213902 [87] Ashalley E, Acheampong K, Besteiro LV, Yu P, Neogi A et al. Multitask deep-learning-based design of chiral plasmonic metamaterials. Photonics Res 8, 1213–1225 (2020). doi: 10.1364/PRJ.388253 [88] Tao ZL, You J, Zhang J, Zheng X, Liu HZ et al. Optical circular dichroism engineering in chiral metamaterials utilizing a deep learning network. Opt Lett 45, 1403–1406 (2020). doi: 10.1364/OL.386980 [89] Tao ZL, Zhang J, You J, Hao H, Ouyang H et al. Exploiting deep learning network in optical chirality tuning and manipulation of diffractive chiral metamaterials. Nanophotonics 9, 2945–2956 (2020). doi: 10.1515/nanoph-2020-0194 [90] Zhu RC, Wang JF, Qiu TS, Sui S, Han YJ et al. Overcome chromatism of metasurface via Greedy Algorithm empowered by self-organizing map neural network. Opt Express 28, 35724–35733 (2020). doi: 10.1364/OE.405856 [91] Lin CH, Chen YS, Lin JT, Wu HC, Kuo HT et al. Automatic inverse design of high-performance beam-steering metasurfaces via genetic-type tree optimization. Nano Lett 21, 4981–4989 (2021). doi: 10.1021/acs.nanolett.1c00720 [92] Zhu RC, Qiu TS, Wang JF, Sui S, Li YF et al. Multiplexing the aperture of a metasurface: inverse design via deep-learning-forward genetic algorithm. J Phys D Appl Phys 53, 455002 (2020). doi: 10.1088/1361-6463/aba64f [93] An XP, Cao Y, Wei YX, Zhou ZH, Hu T et al. Broadband achromatic metalens design based on deep neural networks. Opt Lett 46, 3881–3884 (2021). doi: 10.1364/OL.427221 [94] Fan CY, Su GDJ. Time-effective simulation methodology for broadband achromatic metalens using deep neural networks. Nanomaterials 11, 1966 (2021). doi: 10.3390/nano11081966 [95] Gu YJ, Hao R, Li EP. Independent bifocal metalens design based on deep learning algebra. IEEE Photonics Technol Lett 33, 403–406 (2021). doi: 10.1109/LPT.2021.3066595 [96] Zarei S, Khavasi A. Inverse design of on-chip thermally tunable varifocal metalens based on silicon metalines. IEEE Access 9, 73453–73466 (2021). doi: 10.1109/ACCESS.2021.3079904 [97] Elsawy MMR, Gourdin A, Binois M, Duvigneau R, Felbacq D et al. Multiobjective statistical learning optimization of RGB metalens. ACS Photonics 8, 2498–2508 (2021). doi: 10.1021/acsphotonics.1c00753 [98] Rezaei SD, Dong ZG, Chan JYE, Trisno J, Ng RJH et al. Nanophotonic structural colors. ACS Photonics 8, 18–33 (2021). [99] Lee T, Jang J, Jeong H, Rho J. Plasmonic- and dielectric-based structural coloring: from fundamentals to practical applications. Nano Converg 5, 1 (2018). doi: 10.1186/s40580-017-0133-y [100] Baxter J, Calà Lesina A, Guay JM, Weck A, Berini P et al. Plasmonic colours predicted by deep learning. Sci Rep 9, 8074 (2019). doi: 10.1038/s41598-019-44522-7 [101] Roberts NB, Keshavarz Hedayati M. A deep learning approach to the forward prediction and inverse design of plasmonic metasurface structural color. Appl Phys Lett 119, 061101 (2021). doi: 10.1063/5.0055733 [102] Gao L, Li XZ, Liu DJ, Wang LH, Yu ZF. A bidirectional deep neural network for accurate silicon color design. Adv Mater 31, 1905467 (2019). doi: 10.1002/adma.201905467 [103] Hemmatyar O, Abdollahramezani S, Kiarashinejad Y, Zandehshahvar M, Adibi A. Full color generation with Fano-type resonant HfO2 nanopillars designed by a deep-learning approach. Nanoscale 11, 21266–21274 (2019). doi: 10.1039/C9NR07408B [104] Huang Z, Liu X, Zang JF. The inverse design of structural color using machine learning. Nanoscale 11, 21748–21758 (2019). doi: 10.1039/C9NR06127D [105] Kalt V, González-Alcalde AK, Es-Saidi S, Salas-Montiel R, Blaize S et al. Metamodeling of high-contrast-index gratings for color reproduction. J Opt Soc Am A 36, 79–88 (2019). doi: 10.1364/JOSAA.36.000079 [106] Sajedian I, Badloe T, Rho J. Optimisation of colour generation from dielectric nanostructures using reinforcement learning. Opt Express 27, 5874–5883 (2019). doi: 10.1364/OE.27.005874 [107] González-Alcalde AK, Salas-Montiel R, Kalt V, Blaize S, Macías D. Engineering colors in all-dielectric metasurfaces: metamodeling approach. Opt Lett 45, 89–92 (2020). doi: 10.1364/OL.45.000089 [108] Thompson JR, Burrow JA, Shah PJ, Slagle J, Harpe ES et al. Artificial neural network discovery of a switchable metasurface reflector. Opt Express 28, 24629–24656 (2020). doi: 10.1364/OE.400360 [109] Lio GE, Ferraro A. LIDAR and beam steering tailored by neuromorphic metasurfaces dipped in a tunable surrounding medium. Photonics 8, 65 (2021). doi: 10.3390/photonics8030065 [110] Chen WQ, Zhang DS, Long SY, Liu ZZ, Xiao JJ. Nearly dispersionless multicolor metasurface beam deflector for near eye display designed by a physics-driven deep neural network. Appl Opt 60, 3947–3953 (2021). doi: 10.1364/AO.421901 [111] Shameli MA, Fallah A, Yousefi L. Developing an optimized metasurface for light trapping in thin-film solar cells using a deep neural network and a genetic algorithm. J Opt Soc Am B 38, 2728–2735 (2021). doi: 10.1364/JOSAB.432989 [112] Noureen S, Zubair M, Ali M, Mehmood MQ. Deep learning based hybrid sequence modeling for optical response retrieval in metasurfaces for STPV applications. Opt Mater Express 11, 3178–3193 (2021). doi: 10.1364/OME.424826 [113] McManamon PF. LiDAR Technologies and Systems (SPIE Press, Bellingham, 2019). [114] Maimone A, Georgiou A, Kollin JS. Holographic near-eye displays for virtual and augmented reality. ACM Trans Graph 36, 85 (2017). [115] Koulieris GA, Akşit K, Stengel M, Mantiuk RK, Mania K et al. Near-eye display and tracking technologies for virtual and augmented reality. Comput Graph Forum 38, 493–519 (2019). doi: 10.1111/cgf.13654 [116] Lee GY, Hong JY, Hwang S, Moon S, Kang H et al. Metasurface eyepiece for augmented reality. Nat Commun 9, 4562 (2018). doi: 10.1038/s41467-018-07011-5 [117] Lan SF, Zhang XY, Taghinejad M, Rodrigues S, Lee KT et al. Metasurfaces for near-eye augmented reality. ACS Photonics 6, 864–870 (2019). doi: 10.1021/acsphotonics.9b00180 [118] Long SY, Zhang DY, Liu ZZ, Xiao JJ. Colorful see-through near-eye display based on all-dielectric metasurface. Proc SPIE 11571, 1157106 (2020). [119] Wang C, Yu ZQ, Zhang QB, Sun Y, Tao CN et al. Metalens eyepiece for 3D holographic near-eye display. Nanomaterials 11, 1920 (2021). doi: 10.3390/nano11081920 [120] Bayati E, Wolfram A, Colburn S, Huang LC, Majumdar A et al. Design of achromatic augmented reality visors based on composite metasurfaces. Appl Opt 60, 844–850 (2021). doi: 10.1364/AO.410895 [121] Vulpetti G, Johnson L, Matloff GL. Solar Sails: A Novel Approach to Interplanetary Travel (Springer, New York, 2015);https://doi.org/10.1007/978-1-4939-0941-4. [122] Achouri K, Céspedes OV, Caloz C. Solar “meta-sails” for agile optical force control. IEEE Trans Antennas Propag 67, 6924–6934 (2019). doi: 10.1109/TAP.2019.2925279 [123] Siegel J, Wang AY, Menabde SG, Kats MA, Jang MS et al. Self-stabilizing laser sails based on optical metasurfaces. ACS Photonics 6, 2032–2040 (2019). doi: 10.1021/acsphotonics.9b00484 [124] Salary MM, Mosallaei H. Photonic metasurfaces as relativistic light sails for doppler-broadened stable beam-riding and radiative cooling. Laser Photonics Rev 14, 1900311 (2020). doi: 10.1002/lpor.201900311 [125] Jin WL, Li W, Orenstein M, Fan SH. Inverse design of lightweight broadband reflector for relativistic lightsail propulsion. ACS Photonics 7, 2350–2355 (2020). doi: 10.1021/acsphotonics.0c00768 [126] Salary MM, Mosallaei H. Inverse design of diffractive relativistic meta-sails via multi-objective optimization. Adv Theory Simul 4, 2100047 (2021). doi: 10.1002/adts.202100047 [127] Kudyshev ZA, Kildishev AV, Shalaev VM, Boltasseva A. Optimizing Startshot lightsail design: a generative network-based approach. ArXiv: 2108.12999 (2021). [128] Kudyshev ZA, Kildishev AV, Shalaev VM, Boltasseva A. Machine-learning-assisted metasurface design for high-efficiency thermal emitter optimization. Appl Phys Rev 7, 021407 (2020). doi: 10.1063/1.5134792 [129] Wiecha PR, Lecestre A, Mallet N, Larrieu G. Pushing the limits of optical information storage using deep learning. Nat Nanotechnol 14, 237–244 (2019). doi: 10.1038/s41565-018-0346-1 [130] Balin I, Garmider V, Long Y, Abdulhalim I. Training artificial neural network for optimization of nanostructured VO2-based smart window performance. Opt Express 27, A1030–A1040 (2019). doi: 10.1364/OE.27.0A1030 [131] Abdollahramezani S, Hemmatyar O, Taghinejad M, Taghinejad H, Krasnok A et al. Electrically driven programmable phase-change meta-switch reaching 80% efficiency. ArXiv: 2104.10381 (2021). [132] Zhen Z, Qian C, Jia YT, Fan ZX, Hao R et al. Realizing transmitted metasurface cloak by a tandem neural network. Photonics Res 9, B229–B235 (2021). doi: 10.1364/PRJ.418445 [133] Makarenko M, Wang QZ, Burguete-Lopez A, Getman F, Fratalocchi A. Robust and scalable flat-optics on flexible substrates via evolutionary neural networks. Adv Intell Syst 3, 2100105 (2021). doi: 10.1002/aisy.202100105 [134] Hassan MM, Sium FS, Islam F, Choudhury SM. A review on plasmonic and metamaterial based biosensing platforms for virus detection. Sens Bio-Sens Res 33, 100429 (2021). doi: 10.1016/j.sbsr.2021.100429 [135] Tseng ML, Jahani Y, Leitis A, Altug H. Dielectric metasurfaces enabling advanced optical biosensors. ACS Photonics 8, 47–60 (2021). [136] Zhang SY, Wong CL, Zeng SW, Bi RZ, Tai K et al. Metasurfaces for biomedical applications: imaging and sensing from a nanophotonics perspective. Nanophotonics 10, 259–293 (2021). [137] Tittl A, John-Herpin A, Leitis A, Arvelo ER, Altug H. Metasurface-based molecular biosensing aided by artificial intelligence. Angew Chem Int Ed 58, 14810–14822 (2019). doi: 10.1002/anie.201901443 [138] Son H, Kim SJ, Hong J, Sung J, Lee B. Design of highly perceptible dual-resonance all-dielectric metasurface colorimetric sensor via deep neural networks. (2021);https://doi.org/10.21203/rs.3.rs-801301/v1. [139] Li XZ, Shu J, Gu WH, Gao L. Deep neural network for plasmonic sensor modeling. Opt Mater Express 9, 3857–3862 (2019). doi: 10.1364/OME.9.003857 [140] Yan RQ, Wang T, Jiang XY, Zhong QF, Huang X et al. Design of high-performance plasmonic nanosensors by particle swarm optimization algorithm combined with machine learning. Nanotechnology 31, 375202 (2020). doi: 10.1088/1361-6528/ab95b8 [141] Moon G, Choi JR, Lee C, Oh Y, Kim KH et al. Machine learning-based design of meta-plasmonic biosensors with negative index metamaterials. Biosens Bioelectron 164, 112335 (2020). doi: 10.1016/j.bios.2020.112335 [142] Torun H, Bilgin B, Ilgu M, Yanik C, Batur N et al. Machine learning detects SARS-CoV-2 and variants rapidly on DNA aptamer metasurfaces. medRxiv (2021);https://doi.org/10.1101/2021.08.07.21261749. [143] John-Herpin A, Kavungal D, von Mücke L, Altug H. Infrared metasurface augmented by deep learning for monitoring dynamics between all major classes of biomolecules. Adv Mater 33, 2006054 (2021). doi: 10.1002/adma.202006054 [144] Ren ZH, Zhang ZX, Wei JX, Dong BW, Lee C. Mid-infrared nanoantennas as ultrasensitive vibrational probes assisted by machine learning and hyperspectral imaging. (2021);https://doi.org/10.21203/rs.3.rs-209363/v1. [145] Meng JJ, Cadusch JJ, Crozier KB. Plasmonic mid-infrared filter array-detector array chemical classifier based on machine learning. ACS Photonics 8, 648–657 (2021). doi: 10.1021/acsphotonics.0c01786 [146] Jamshidi M, Lalbakhsh A, Talla J, Peroutka Z, Hadjilooei F et al. Artificial intelligence and COVID-19: deep learning approaches for diagnosis and treatment. IEEE Access 8, 109581–109595 (2020). doi: 10.1109/ACCESS.2020.3001973 [147] Kwekha-Rashid AS, Abduljabbar HN, Alhayani B. Coronavirus disease (COVID-19) cases analysis using machine-learning applications. Appl Nanosci (2021);https://doi.org/10.1007/s13204-021-01868-7. [148] Liu FF, Zhang WH, Sun Y, Liu JW, Miao JG et al. Secure deep learning for intelligent terahertz metamaterial identification. Sensors 20, 5673 (2020). doi: 10.3390/s20195673 [149] Cui FY, Yue Y, Zhang Y, Zhang ZM, Zhou HS. Advancing biosensors with machine learning. ACS Sens 5, 3346–3364 (2020). doi: 10.1021/acssensors.0c01424 [150] Banerjee A, Maity S, Mastrangelo CH. Nanostructures for biosensing, with a brief overview on cancer detection, IoT, and the role of machine learning in smart biosensors. Sensors 21, 1253 (2021). doi: 10.3390/s21041253 [151] Blevins MG, Fernandez-Galiana A, Hooper MJ, Boriskina SV. Roadmap on universal photonic biosensors for real-time detection of emerging pathogens. Photonics 8, 342 (2021). doi: 10.3390/photonics8080342 [152] Haick H, Tang N. Artificial intelligence in medical sensors for clinical decisions. ACS Nano 15, 3557–3567 (2021). doi: 10.1021/acsnano.1c00085 [153] Cui TJ, Qi MQ, Wan X, Zhao J, Cheng Q. Coding metamaterials, digital metamaterials and programmable metamaterials. Light Sci Appl 3, e218 (2014). doi: 10.1038/lsa.2014.99 [154] Li LL, Cui TJ. Information metamaterials – from effective media to real-time information processing systems. Nanophotonics 8, 703–724 (2019). doi: 10.1515/nanoph-2019-0006 [155] Abadal S, Cui TJ, Low T, Georgiou J. Programmable metamaterials for software-defined electromagnetic control: circuits, systems, and architectures. IEEE J Emerg Sel Top Circuits Syst 10, 6–19 (2020). doi: 10.1109/JETCAS.2020.2976165 [156] Bao L, Cui TJ. Tunable, reconfigurable, and programmable metamaterials. Microw Opt Technol Lett 62, 9–32 (2020). doi: 10.1002/mop.32164 [157] Cui TJ, Li LL, Liu S, Ma Q, Zhang L et al. Information metamaterial systems. iScience 23, 101403 (2020). doi: 10.1016/j.isci.2020.101403 [158] Ma Q, Cui TJ. Information Metamaterials: bridging the physical world and digital world. PhotoniX 1, 1 (2020). doi: 10.1186/s43074-020-00006-w [159] Tsilipakos O, Tasolamprou AC, Pitilakis A, Liu F, Wang XC et al. Toward intelligent metasurfaces: the progress from globally tunable metasurfaces to software-defined metasurfaces with an embedded network of controllers. Adv Opt Mater 8, 2000783 (2020). doi: 10.1002/adom.202000783 [160] Luo SS, Hao JJ, Ye FJ, Li JX, Ruan Y et al. Evolution of the electromagnetic manipulation: from tunable to programmable and intelligent metasurfaces. Micromachines 12, 988 (2021). doi: 10.3390/mi12080988 [161] Zhang Q, Liu C, Wan X, Zhang L, Liu S et al. Machine-learning designs of anisotropic digital coding metasurfaces. Adv Theory Simul 2, 1800132 (2019). doi: 10.1002/adts.201800132 [162] Banerji S, Majumder A, Hamrick A, Menon R, Sensale-Rodriguez B. Machine learning enables ultra-compact integrated photonics through silicon-nanopattern digital metamaterials. ArXiv: 2011.11754 (2020). [163] Shan T, Pan XT, Li MK, Xu SS, Yang F. Coding programmable metasurfaces based on deep learning techniques. IEEE J Emerg Sel Top Circuits Syst 10, 114–125 (2020). doi: 10.1109/JETCAS.2020.2972764 [164] Abdullah M, Koziel S. Supervised-learning-based development of multibit RCS-reduced coding metasurfaces. IEEE Trans Microw Theory Tech (2021);https://doi.org/10.1109/TMTT.2021.3105677. [165] Liu C, Yu WM, Ma Q, Li LL, Cui TJ. Intelligent coding metasurface holograms by physics-assisted unsupervised generative adversarial network. Photonics Res 9, B159–B167 (2021). doi: 10.1364/PRJ.416287 [166] Sui FP, Guo RQ, Zhang ZZ, Gu GX, Lin LW. Deep reinforcement learning for digital materials design. ACS Mater Lett 3, 1433–1439 (2021). doi: 10.1021/acsmaterialslett.1c00390 [167] Yang S, Zhang K, Ding XM, Yang GH, Wu Q. Tailoring the scattering properties of coding metamaterials based on machine learning. EPJ Appl Metamat 8, 15 (2021). doi: 10.1051/epjam/2021006 [168] Di Renzo M, Debbah M, Phan-Huy DT, Zappone A, Alouini MS et al. Smart radio environments empowered by reconfigurable AI meta-surfaces: an idea whose time has come. EURASIP J Wirel Commun Netw 2019, 129 (2019). doi: 10.1186/s13638-019-1438-9 [169] Di Renzo M, Zappone A, Debbah M, Alouini MS, Yuen C et al. Smart radio environments empowered by reconfigurable intelligent surfaces: how it works, state of research, and the road ahead. IEEE J Sel Areas Commun 38, 2450–2525 (2020). doi: 10.1109/JSAC.2020.3007211 [170] Gong SM, Lu X, Hoang DT, Niyato D, Shu L et al. Toward smart wireless communications via intelligent reflecting surfaces: a contemporary survey. IEEE Commun Surv Tutor 22, 2283–2314 (2020). doi: 10.1109/COMST.2020.3004197 [171] Alexandropoulos GC, Shlezinger N, Alamzadeh I, Imani MF, Zhang HY et al. Hybrid reconfigurable intelligent metasurfaces: enabling simultaneous tunable reflections and sensing for 6G wireless communications. ArXiv: 2104.04690 (2021). [172] Liu YW, Liu X, Mu XD, Hou TW, Xu JQ et al. Reconfigurable intelligent surfaces: principles and opportunities. IEEE Commun Surv Tutor 23, 1546–1577 (2021). doi: 10.1109/COMST.2021.3077737 [173] Long WX, Chen R, Moretti M, Zhang W, Li JD. A promising technology for 6G wireless networks: intelligent reflecting surface. J Commun Inf Netw 6, 1–16 (2021). [174] Munochiveyi M, Pogaku AC, Do DT, Le AT, Voznak M et al. Reconfigurable intelligent surface aided multi-user communications: state-of-the-art techniques and open issues. IEEE Access 9, 118584–118605 (2021). doi: 10.1109/ACCESS.2021.3107316 [175] Wang JH, Tang WK, Han Y, Jin S, Li X et al. Interplay between RIS and AI in wireless communications: fundamentals, architectures, applications, and open research problems. IEEE J Sel Areas Commun 39, 2271–2288 (2021). doi: 10.1109/JSAC.2021.3087259 [176] Lee KT, Ji CG, Iizuka H, Banerjee D. Optical cloaking and invisibility: from fiction toward a technological reality. J Appl Phys 129, 231101 (2021). doi: 10.1063/5.0048846 [177] Qian C, Zheng B, Shen YC, Jing L, Li EP et al. Deep-learning-enabled self-adaptive microwave cloak without human intervention. Nat Photonics 14, 383–390 (2020). doi: 10.1038/s41566-020-0604-2 [178] Qian C, Chen HS. A perspective on the next generation of invisibility cloaks—Intelligent cloaks. Appl Phys Lett 118, 180501 (2021). doi: 10.1063/5.0049748 [179] Li LL, Ruan HX, Liu C, Li Y, Shuang Y et al. Machine-learning reprogrammable metasurface imager. Nat Commun 10, 1082 (2019). doi: 10.1038/s41467-019-09103-2 [180] Li LL, Shuang Y, Ma Q, Li HY, Zhao HT et al. Intelligent metasurface imager and recognizer. Light Sci Appl 8, 97 (2019). doi: 10.1038/s41377-019-0209-z [181] Tseng E, Colburn S, Whitehead J, Huang LC, Baek SH et al. Neural nano-optics for high-quality thin lens imaging. Nat Commun 12, 6493 (2021). doi: 10.1038/s41467-021-26443-0 [182] Cui TJ, Liu C, Ma Q, Luo ZJ, Hong QR et al. Programmable artificial intelligence machine for wave sensing and communications. (2020); https://doi.org/10.21203/rs.3.rs-90701/v1. [183] del Hougne P, Imani MF, Diebold AV, Horstmeyer R, Smith DR. Learned integrated sensing pipeline: reconfigurable metasurface transceivers as trainable physical layer in an artificial neural network. Adv Sci 7, 1901913 (2020). doi: 10.1002/advs.201901913 [184] Li HY, Zhao HT, Wei ML, Ruan HX, Shuang Y et al. Intelligent electromagnetic sensing with learnable data acquisition and processing. Patterns 1, 100006 (2020). doi: 10.1016/j.patter.2020.100006 [185] Saigre-Tardif C, Faqiri R, Zhao HT, Li LL, del Hougne P. Intelligent meta-imagers: from compressed to learned sensing. ArXiv: 2110.14022 (2021). [186] Shastri BJ, Tait AN, Ferreira de Lima T, Pernice WHP, Bhaskaran H et al. Photonics for artificial intelligence and neuromorphic computing. Nat Photonics 15, 102–114 (2021). doi: 10.1038/s41566-020-00754-y [187] Xiang SY, Han YN, Song ZW, Guo XX, Zhang YH et al. A review: photonics devices, architectures, and algorithms for optical neural computing. J Semicond 42, 023105 (2021). doi: 10.1088/1674-4926/42/2/023105 [188] Burgos CMV, Yang TQ, Zhu YH, Vamivakas AN. Design framework for metasurface optics-based convolutional neural networks. Appl Opt 60, 4356–4365 (2021). doi: 10.1364/AO.421844 [189] Luo XH, Hu YQ, Li X, Ou XN, Lai JJ et al. Metasurface-enabled on-chip multiplexed diffractive neural networks in the visible. ArXiv: 2107.07873 (2021). [190] Pu GQ, Zhang L, Hu WS, Yi LL. Automatic mode-locking fiber lasers: progress and perspectives. Sci China Inf Sci 63, 160404 (2020). doi: 10.1007/s11432-020-2883-0 [191] Wang HF, Gupta SK, Xie BY, Lu MH. Topological photonic crystals: a review. Front Optoelectron 13, 50–72 (2020). doi: 10.1007/s12200-019-0949-7 [192] Segev M, Bandres MA. Topological photonics: where do we go from here. Nanophotonics 10, 425–434 (2021). [193] Singh R, Agarwal A, Anthony BW. Mapping the design space of photonic topological states via deep learning. Opt Express 28, 27893–27902 (2020). doi: 10.1364/OE.398926 [194] Pilozzi L, Farrelly FA, Marcucci G, Conti C. Machine learning inverse problem for topological photonics. Commun Phys 1, 57 (2018). doi: 10.1038/s42005-018-0058-8 [195] Long Y, Ren J, Li YH, Chen H. Inverse design of photonic topological state via machine learning. Appl Phys Lett 114, 181105 (2019). doi: 10.1063/1.5094838 [196] Pilozzi L, Farrelly FA, Marcucci G, Conti C. Topological nanophotonics and artificial neural networks. Nanotechnology 32, 142001 (2021). doi: 10.1088/1361-6528/abd508 [197] Wu B, Ding K, Chan CT, Chen YT. Machine prediction of topological transitions in photonic crystals. Phys Rev Appl 14, 044032 (2020). doi: 10.1103/PhysRevApplied.14.044032 [198] Chen M, Zandehshahvar M, Kiarashinejad Y, Hemmatyar O, Umapathy D et al. Inverse design of nanophotonic structures using a hybrid dimensionality reduction technique. In Proceedings of Frontiers in Optics / Laser Science FM2A. 1 (Optical Society of America, 2020);https://doi.org/10.1364/FIO.2020.FM2A.1. [199] Nussbaum E, Sauer E, Hughes S. Inverse design of broadband and lossless topological photonic crystal waveguide modes. Opt Lett 46, 1732–1735 (2021). doi: 10.1364/OL.420080 [200] Zhirihin DV, Kivshar YS. Topological photonics on a small scale. Small Sci 1, 2100065 (2021). doi: 10.1002/smsc.202100065 [201] Koshelev K, Bogdanov A, Kivshar Y. Meta-optics and bound states in the continuum. Sci Bull 64, 836–842 (2019). doi: 10.1016/j.scib.2018.12.003 [202] Ma XZ, Ma Y, Cunha P, Liu QS, Kudtarkar K et al. A universal deep learning strategy for designing high-quality-factor photonic resonances. ArXiv: 2105.03001 (2021). [203] Lin RH, Alnakhli Z, Li XH. Engineering of multiple bound states in the continuum by latent representation of freeform structures. Photonics Res 9, B96–B103 (2021). doi: 10.1364/PRJ.415655 [204] Azzam SI, Kildishev AV. Photonic bound states in the continuum: from basics to applications. Adv Opt Mater 9, 2001469 (2021). doi: 10.1002/adom.202001469 [205] Sadreev AF. Interference traps waves in an open system: bound states in the continuum. Rep Prog Phys 84, 055901 (2021). doi: 10.1088/1361-6633/abefb9 [206] Wang ZD, Qian C, Cai T, Tian LW, Fan ZX et al. Demonstration of spider-eyes-like intelligent antennas for dynamically perceiving incoming waves. Adv Intell Syst 3, 2100066 (2021). doi: 10.1002/aisy.202100066 [207] Schuman CD, Potok TE, Patton RM, Birdwell JD, Dean ME et al. A survey of neuromorphic computing and neural networks in hardware. ArXiv: 1705.06963 (2017). [208] Shen YC, Harris NC, Skirlo S, Prabhu M, Baehr-Jones T et al. Deep learning with coherent nanophotonic circuits. Nat Photonics 11, 441–446 (2017). doi: 10.1038/nphoton.2017.93 [209] Hughes TW, Minkov M, Shi Y, Fan SH. Training of photonic neural networks through in situ backpropagation and gradient measurement. Optica 5, 864–871 (2018). doi: 10.1364/OPTICA.5.000864 [210] Feldmann J, Youngblood N, Wright CD, Bhaskaran H, Pernice WHP. All-optical spiking neurosynaptic networks with self-learning capabilities. Nature 569, 208–214 (2019). doi: 10.1038/s41586-019-1157-8 [211] Lin X, Rivenson Y, Yardimci NT, Veli M, Luo Y et al. All-optical machine learning using diffractive deep neural networks. Science 361, 1004–1008 (2018). doi: 10.1126/science.aat8084 [212] Getman F, Makarenko M, Burguete-Lopez A, Fratalocchi A. Broadband vectorial ultrathin optics with experimental efficiency up to 99% in the visible region via universal approximators. Light Sci Appl 10, 47 (2021). doi: 10.1038/s41377-021-00489-7 [213] Wright LG, Onodera T, Stein MM, Wang TY, Schachter DT et al. Deep nonlinear optical neural networks using physics-aware training. In Proceedings of Conference on Lasers and Electro-Optics FF1A. 4 (Optical Society of America, 2021);https://doi.org/10.1364/CLEO_QELS.2021.FF1A.4. [214] Majumdar A. Metaphotonic computational image sensors. In Proceedings of Imaging and Applied Optics Congress IW1D. 3 (Optical Society of America, 2020);https://doi.org/10.1364/ISA.2020.IW1D.3. [215] Specht DF. A general regression neural network. IEEE Trans Neural Netw 2, 568–576 (1991). doi: 10.1109/72.97934 [216] Lee K, Han H, Kim Y, Park J, Jang S et al. Retina-inspired structurally tunable synaptic perovskite nanocones. Adv Funct Mater 31, 2105596 (2021). doi: 10.1002/adfm.202105596 [217] Hu JT, Liu TT, Choo P, Wang SJ, Reese T et al. Single-nanoparticle orientation sensing by deep learning. ACS Cent Sci 6, 2339–2346 (2020). doi: 10.1021/acscentsci.0c01252 [218] Shiratori K, Bishop LDC, Ostovar B, Baiyasi R, Cai YY et al. Machine-learned decision trees for predicting gold nanorod sizes from spectra. J Phys Chem C 125, 19353–19361 (2021). doi: 10.1021/acs.jpcc.1c03937 [219] Pu TC, Ou JY, Savinov V, Yuan GH, Papasimakis N et al. Unlabeled far-field deeply subwavelength topological microscopy (DSTM). Adv Sci 8, 2002886 (2021). doi: 10.1002/advs.202002886 [220] Shao SY, Mallery K, Kumar SS, Hong JR. Machine learning holography for 3D particle field imaging. Opt Express 28, 2987–2999 (2020). doi: 10.1364/OE.379480 [221] Wang Q, He H, Zhang Q, Feng ZZ, Li JQ et al. Deep-learning-assisted single-molecule tracking on a live cell membrane. Anal Chem 93, 8810–8816 (2021). doi: 10.1021/acs.analchem.1c00547 [222] Speiser A, Müller LR, Hoess P, Matti U, Obara CJ et al. Deep learning enables fast and dense single-molecule localization with high accuracy. Nat Methods 18, 1082–1090 (2021). doi: 10.1038/s41592-021-01236-x [223] Zhang PY, Liu S, Chaurasia A, Ma DH, Mlodzianoski MJ et al. Analyzing complex single-molecule emission patterns with deep learning. Nat Methods 15, 913–916 (2018). doi: 10.1038/s41592-018-0153-5 [224] Tranter AD, Slatyer HJ, Hush MR, Leung AC, Everett JL et al. Multiparameter optimisation of a magneto-optical trap using deep learning. Nat Commun 9, 4360 (2018). doi: 10.1038/s41467-018-06847-1 [225] Gupta RK, Everett JL, Tranter AD, Henke R, Gokhroo V et al. Machine learner optimization of optical nanofiber-based dipole traps for cold 87Rb atoms. ArXiv: 2110.03931 (2021). [226] Wigley PB, Everitt PJ, van den Hengel A, Bastian JW, Sooriyabandara MA et al. Fast machine-learning online optimization of ultra-cold-atom experiments. Sci Rep 6, 25890 (2016). doi: 10.1038/srep25890 [227] Henson BM, Shin DK, Thomas KF, Ross JA, Hush MR et al. Approaching the adiabatic timescale with machine learning. Proc Natl Acad Sci USA 115, 13216–13221 (2018). doi: 10.1073/pnas.1811501115 -
Access History
Figures(7)
Article Metrics
Export File
Citation
Format
Content
DownLoad:
-
Figure 1.
Links of different ML-based concepts. Artificial intelligence (AI) is a part of computer science dedicated to development of ways to mimic general intelligence. Machine learning (ML) is a subset of AI, these are data-driven algorithms which learn from experience and have the capacity to improve their performance over time and adapt to new data. ML algorithms are varied in their approach, however deep learning (DL) is a subset of ML solely based on layered structures referred to as artificial neural networks. The main feature of DL is the capability to efficiently process raw unstructured data and automatically determine its features while classical ML involves the processing of data in a manner predefined by a human operator.
-
Figure 2.
Inverse and forward designs based on DL techniques. An artificial neural network is fed by parameters of a structure and the corresponding physical response is obtained with conventional numerical techniques or from an experiment. Structure parameters may come in a form of numerical arrays containing geometric or material parameters, or in a form of images or sets of pixels. During the training procedure the neural network determines the appropriate mapping to account for the relation between the parameters and the responses. Then, the network can predict a structure response which was not present in the learning set of data – this is a forward design, which is a prediction of a physical response for a given structure. Swapping the input and output data and applying the similar training procedure, the network may provide a reverse function, predicting parameters of a structure which allows achieving a given physical response, called an inverse design.
-
Figure 3.
ML-empowered designs of multilayer nanoantennas. (a) Schematic of the design procedure based on the DL approaches. A DL algorithm (a black box) connects physical response with parameters of a structure. For example, hand-drawn scattering spectra can be processed with the black-box in order to define materials and thicknesses of the layers needed to achieve target spectra (Based on the results from ref.38). (b) Demonstration of invisibility-to-superscattering transition of a multilayer sphere made of phase-change materials. Materials and thicknesses for this case are found similar to the scheme in (a)48. (c) Transfer learning process. Layers of one trained ANN can be merged with another ANN to provide a training procedure for another type of the structure. This might be used for a design of multilayer films or multilayer sphere with using the ANN approach (Concept originates from the results of refs.52, 53). Figure reproduced with permission from: (b) ref.48, Optica Publishing Group.
-
Figure 4.
ML-empowered designs of transformative metasurfaces. (a) General scheme of the inverse design implemented for metasurfaces. Representation of metasurface elements can be done in several ways. For example, DL may process parameters of unit cells with a fixed geometry. At the same time, free-form design can be implemented, such as unit cells are represented as sets of pixelated images. DL-supplemented design of metasurfaces enable achieving of a great variety of devices, such as multi-resonant and broadband absorbers, metalenses with dual independent focal points, switchable reflectors, and structures with desired circular dichroism. (b) Example of the LIDAR device consisting of two ITO electrodes containing the metastructures filled with the liquid crystal. Voltages applied to electrodes are controlled via FPGA processor. Metasurfaces deflects the transmitted beam at the desired angle via tuning of the refractive index. (c) Configuration of binocular near-eye display utilizing beam splitters as in-coupling gratings. The optimised grating design is shown in the inset as well as RGB model of the beam-splitter and electric intensity above the grating. Figure reproduced with permission from: (a) refs.59, 60, under the Creative Commons Attribution 4.0 International License, refs.84, 108, Optica Publishing Group, ref.95, IEEE; (b) ref.109, under a Creative Commons Attribution 4.0 International license; (c) ref.110, Optica Publishing Group.
-
Figure 5.
DL-empowered metasensors. (a) Schematic of sensing applications of metasurfaces empowered by the of DL methods. DL serves as a tool for designing metasurfaces used as sensing platforms or for analysing measured response spectra and its classification for the presence of specific molecules, etc. (b) Example of a colorimetric sensor inversely designed with the DL approach. Design procedure implies achieving of a target dual-resonant spectra for a double-bar unit cell. As a result, the sensor is capable to distinguish refractive indexes differed in values by less than 0.01. (c) DL-supported classification of SARS-CoV-2. Here, unit cell and Raman shift spectra are shown, where P.A. stands for the primary aptamer and S.A. is for the secondary aptamer. Confusion matrix is composed for DL-based classification of clinical samples. (d) Example of a plasmonic sensor for monitoring biomolecule dynamics. Real-time analysis of absorbance spectra via ML methods allows to distinguish between dynamically changing biological samples. In particular, regression signal allows tracking dynamics of liposome nanoparticles loaded with sucrose and nucleotides. Introduction of melittin results in perforation of lipid membranes and cargo release followed by formation of lipid bilayer. This process can be tracked with the help of ML. Figure reproduced with permission from: (b) ref.138, under a Creative Commons Attribution 4.0 InternationalLicense; (c) ref.142, the authors; (d) ref.143, under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
-
Figure 6.
Self-adapting metasurfaces. (a) General schematic of DL-assisted self-adaptive metadevices. Programmable metasurfaces are controlled via a DL algorithm processing incoming signal. A change of environment leads to a change of coding sequences required to adjust the response of a metasurface. (b) Example of a self-adapting cloaking device. An object is covered by a metacloak made of varactor diodes. Data from sensors perceiving changes in background is processed by a DL algorithm determining voltages required to apply to diodes to adjust the cloak. (c) DL-assisted microwave imager based on a metasurface. Microwave data coming to a metasurface is processed via DL algorithm to reconstruct image of a human. Another DL algorithm can be used for recognition of specific regions within the reconstructed image, such as hands (gestures). Additionally, the collected data may be used for identification of human breath. (d) Metasurface-based optical ANN with re-programmable functions. Digital metasurfaces are used as a physical layer of the network with programming sequences controlled by FPGA processor. The network can dynamically change its functions via re-training procedure. Figure reproduced with permission from: (b) ref.177, Springer Nature; (c) ref.180, (d) ref.182, under a Creative Commons Attribution 4.0 International License.
-
Figure 7.
Examples of DL-empowered metasystems. (a) Forward and inverse design procedures for topological properties of 1D photonic crystal. Labels 0 and 1 indicate geometric Zak phase of bands (which is either 0 or π, correspondingly). (Adapted from refs.193, 197). (b) Bound states in the continuum designed via DL algorithm, which allowed to predict reflection spectra with automatically labelled modes and find suitable geometric parameters of a unit cell. The results of the design procedure were confirmed experimentally by angle-resolved measurements. (Adapted from ref.202). (c) Example of biology-inspired system incorporating DL algorithms. Here, spider-eye-like system is presented, where antenna is used to perceive incoming waves and process them to retrieve information about the environment. ANN in this case explicitly imitates the work of a biological neural network, realizing a system similar to a vision system of a spider. (Adapted from ref.206) Figure reproduced with permission from: (a) ref.193, Optica Publishing Group, ref.197, American Physical Society; (b) ref.202, the authors; (c) ref.206, under a Creative Commons Attribution 4.0 International License.
