Teaching optics to a machine learning network.

In this Letter, we demonstrate how harmonic oscillator equations can be integrated in a neural network to improve the spectral response prediction for an optical system. We use the optical properties of a one-dimensional nanoslit array for a practical implementation of the study. This method allows to build more generalizable relations between the input parameters of the array and its optical properties, showing a 20-fold improvement for parameters outside the range used for the training. We also show how this model generates the output spectrum from phenomenological relationships between the input parameters and the output spectrum, indicating how it grasps the physical mechanisms of the optical response of the structure.

[1]  Iman Sajedian,et al.  Predicting resonant properties of plasmonic structures by deep learning , 2018, ArXiv.

[2]  Olivier J. F. Martin,et al.  Controlling the Fano interference in a plasmonic lattice , 2007 .

[3]  Feng Cheng,et al.  Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy , 2019, Advanced materials.

[4]  Michael Mrejen,et al.  Plasmonic nanostructure design and characterization via Deep Learning , 2018, Light: Science & Applications.

[5]  Benjamin Gallinet,et al.  Color-Selective and Versatile Light Steering with up-Scalable Subwavelength Planar Optics , 2017 .

[6]  Pierre Berini,et al.  Plasmonic colours predicted by deep learning , 2019, Scientific Reports.

[7]  Chen Yan,et al.  Fano-resonance-assisted metasurface for color routing , 2017, Light: Science & Applications.

[8]  Aram Amassian,et al.  Impressive near-infrared brightness and singlet oxygen generation from strategic lanthanide–porphyrin double-decker complexes in aqueous solution , 2019, Light: Science & Applications.

[9]  Zongfu Yu,et al.  Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures , 2017, 2019 Conference on Lasers and Electro-Optics (CLEO).

[10]  Peter R. Wiecha,et al.  Pushing the limits of optical information storage using deep learning , 2018, Nature Nanotechnology.

[11]  Piyush M. Tagade,et al.  Attribute driven inverse materials design using deep learning Bayesian framework , 2019, npj Computational Materials.

[12]  Yongmin Liu,et al.  Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials. , 2018, ACS nano.

[13]  Benjamin Gallinet,et al.  Ab initio theory of Fano resonances in plasmonic nanostructures and metamaterials , 2011, 1105.2503.

[14]  Xu Han,et al.  Efficient spectrum prediction and inverse design for plasmonic waveguide systems based on artificial neural networks , 2018, Photonics Research.

[15]  A. F. J. Levi,et al.  Essential Classical Mechanics for Device Physics , 2016 .

[16]  Junsuk Rho,et al.  Designing nanophotonic structures using conditional deep convolutional generative adversarial networks , 2019, Nanophotonics.

[17]  A. Matsko,et al.  Probing 10 μK stability and residual drifts in the cross-polarized dual-mode stabilization of single-crystal ultrahigh-Q optical resonators , 2019, Light, science & applications.

[18]  A. B. Kadykov,et al.  Investigation of the generalizing capabilities of convolutional neural networks in forming rotation-invariant attributes , 2015 .

[19]  Yi Yang,et al.  Nanophotonic particle simulation and inverse design using artificial neural networks , 2018, Science Advances.

[20]  Trevon Badloe,et al.  Finding the best design parameters for optical nanostructures using reinforcement learning , 2018, ArXiv.

[21]  Yuri S. Kivshar,et al.  Fano resonances in photonics , 2017, Nature Photonics.

[22]  J. P. Woerdman,et al.  Fano-type interpretation of red shifts and red tails in hole array transmission spectra , 2003, physics/0401054.

[23]  Michel Meunier,et al.  Sensing with periodic nanohole arrays , 2017 .

[24]  H. Lezec,et al.  Extraordinary optical transmission through sub-wavelength hole arrays , 1998, Nature.

[25]  Kyu-Tae Lee,et al.  A Generative Model for Inverse Design of Metamaterials , 2018, Nano letters.

[26]  Toshiaki Koike-Akino,et al.  Deep Neural Network Inverse Design of Integrated Nanophotonic Devices. , 2018, 1809.03555.

[27]  Yuebing Zheng,et al.  Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale , 2018, Nanophotonics.