Intelligent metaphotonics empowered by machine learning

Abstract

In the recent years, we observe a dramatic boost of research in photonics empowered by the concepts of machine learning and artificial intelligence. The corresponding photonic systems, to which this new methodology is applied, can range from traditional optical waveguides to nanoantennas and metasurfaces, and these novel approaches underpin the fundamental principles of light-matter interaction developed for a smart design of intelligent photonic devices. Concepts and approaches of 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 introduce this new field with its application to metaphotonics and also present a summary of the basic concepts of machine learning with some specific examples developed and demonstrated for metasystems and metasurfaces.

References in corpus (45)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning with Coherent Nanophotonic Circuits
• Language Models are Few-Shot Learners
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Photonics for artificial intelligence and neuromorphic computing
• Explainable Machine Learning for Scientific Insights and Discoveries
• Towards Smart Wireless Communications via Intelligent Reflecting Surfaces: A Contemporary Survey
• A high-bias, low-variance introduction to Machine Learning for physicists
• High-Q supercavity modes in subwavelength dielectric resonators
• Metalenses at visible wavelengths: past, present, perspectives
• Training of photonic neural networks through in situ backpropagation
• Electrically driven programmable phase-change meta-switch reaching 80% efficiency
• A Survey of Neuromorphic Computing and Neural Networks in Hardware
• Neural Nano-Optics for High-quality Thin Lens Imaging
• Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
• Interference traps waves in open system: Bound states in the continuum
• Machine-Learning-Assisted Metasurface Design for High-Efficiency Thermal Emitter Optimization
• Fast machine-learning online optimization of ultra-cold-atom experiments
• Machine Learning for Quantum Matter
• Artificial Neural Network with Physical Dynamic Metasurface Layer for Optimal Sensing
• Pushing the limits of optical information storage using deep learning
• Plasmonic colours predicted by deep learning
• Multiparameter optimisation of a magneto-optical trap using deep learning
• An Efficient Deep Learning Technique for the Navier-Stokes Equations: Application to Unsteady Wake Flow Dynamics
• Machine Learning Holography for 3D Particle Field Imaging
• Intelligent Meta-Imagers: From Compressed to Learned Sensing
• Machine Learning for Condensed Matter Physics
• Biomimetic Ultra-Broadband Perfect Absorbers Optimised with Reinforcement Learning
• Interplay between RIS and AI in Wireless Communications: Fundamentals, Architectures, Applications, and Open Research Problems
• Plasmonic metamaterial based virus detection system: a review
• Mapping the Design Space of Photonic Topological States via Deep Learning
• Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
• A Combined Machine-Learning / Optimization-Based Approach for Inverse Design of Nonuniform Bianisotropic Metasurfaces
• Approaching the adiabatic timescale with machine-learning
• Design of achromatic augmented reality visors based on composite metasurfaces
• Physics-aware deep neural networks for surrogate modeling of turbulent natural convection
• Deep-Learning-Enabled Inverse Engineering of Multi-Wavelength Invisibility-to-Superscattering Switching with Phase-Change Materials
• Inverse design of broadband and lossless topological photonic crystal waveguide modes
• Machine prediction of topological transitions in photonic crystals
• MaxwellNet: Physics-driven deep neural network training based on Maxwell's equations
• A universal deep learning strategy for designing high-quality-factor photonic resonances
• Inverse design of multilayer nanoparticles using artificial neural networks and genetic algorithm
• Interpretable inverse design of particle spectral emissivity using machine learning
• Machine Learning enables Ultra-Compact Integrated Photonics through Silicon-Nanopattern Digital Metamaterials
• Topological Photonics on a Small Scale

Cited by in corpus (5)

• A neural operator-based surrogate solver for free-form electromagnetic inverse design
• Simultaneously realizing thermal and electromagnetic cloaking by multi-physical null medium
• Inverse Design of All-dielectric Metasurfaces with Bound States in the Continuum
• Inverse design of Mie resonators with minimal backscattering
• Experimental realization of the active convolved illumination imaging technique for enhanced signal-to-noise ratio