Deep neural networks for the evaluation and design of photonic devices

Abstract

The data sciences revolution is poised to transform the way photonic systems are simulated and designed. Photonics are in many ways an ideal substrate for machine learning: the objective of much of computational electromagnetics is the capture of non-linear relationships in high dimensional spaces, which is the core strength of neural networks. Additionally, the mainstream availability of Maxwell solvers makes the training and evaluation of neural networks broadly accessible and tailorable to specific problems. In this Review, we will show how deep neural networks, configured as discriminative networks, can learn from training sets and operate as high-speed surrogate electromagnetic solvers. We will also examine how deep generative networks can learn geometric features in device distributions and even be configured to serve as robust global optimizers. Fundamental data sciences concepts framed within the context of photonics will also be discussed, including the network training process, delineation of different network classes and architectures, and dimensionality reduction.

arXiv commentReview paper

References in corpus (34)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Deep Learning with Coherent Nanophotonic Circuits
• Photonic quantum technologies
• Conditional Image Generation with PixelCNN Decoders
• Training deep neural networks for the inverse design of nanophotonic structures
• Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer
• A Generative Model for Inverse Design of Metamaterials
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Fully integrated ultra-low power Kerr comb generation
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
• Wave Physics as an Analog Recurrent Neural Network
• Learning to learn by gradient descent by gradient descent
• Adjoint method and inverse design for nonlinear nanophotonic devices
• Intelligent Nanophotonics: Merging Photonics and Artificial Intelligence at the Nanoscale
• Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
• Inverse design of photonic crystals through automatic differentiation
• Optimization of photonic crystal nanocavities based on deep learning
• Machine-Learning-Assisted Metasurface Design for High-Efficiency Thermal Emitter Optimization
• Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures
• Efficient spectrum prediction and inverse design for plasmonic waveguide systems based on artificial neural networks
• Simulator-based training of generative models for the inverse design of metasurfaces
• Mapping the global design space of nanophotonic components using machine learning pattern recognition
• Enhanced Light-Matter Interactions in Dielectric Nanostructures via Machine Learning Approach
• Benchmarking five global optimization approaches for nano-optical shape optimization and parameter reconstruction
• Knowledge Discovery In Nanophotonics Using Geometric Deep Learning
• Forward-Mode Differentiation of Maxwell's Equations
• Freeform metagratings based on complex light scattering dynamics for extreme, high efficiency beam steering
• Designing Silicon Photonic Devices using Artificial Neural Networks
• MetaNet: A new paradigm for data sharing in photonics research
• Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks
• Mapping the Design Space of Photonic Topological States via Deep Learning
• A topological encoding method for data-driven photonics inverse design
• Multifunctional Metasurface Design with a Generative Adversarial Network

Cited by in corpus (50)

• Inverse design enables large-scale high-performance meta-optics reshaping virtual reality
• On the use of Artificial Neural Networks in Topology Optimisation
• Minireview on Disordered Optical Metasurfaces
• Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
• Deep learning enabled design of complex transmission matrices for universal optical components
• A newcomer's guide to deep learning for inverse design in nano-photonics
• Super-resolution image display using diffractive decoders
• Artificial Intelligence in Material Engineering: A review on applications of AI in Material Engineering
• Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks
• Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
• Enhancing Adjoint Optimization-based Photonics Inverse Design with Explainable Machine Learning
• Deep learning enabled strategies for modelling of complex aperiodic plasmonic metasurfaces of arbitrary size
• Machine Learning Framework for Quantum Sampling of Highly-Constrained, Continuous Optimization Problems
• On the influence of over-parameterization in manifold based surrogates and deep neural operators
• Inverse Design of Grating Couplers Using the Policy Gradient Method from Reinforcement Learning
• Deep learning-based design of broadband GHz complex and random metasurfaces
• Integrated Photonic Platforms for Quantum Technology: A Review
• Free-form inverse design of arbitrary dispersive materials in nanophotonics
• Inverse design with flexible design targets via deep learning: Tailoring of electric and magnetic multipole scattering from nano-spheres
• Inverse Design of All-dielectric Metasurfaces with Bound States in the Continuum
• GRIDS-Net: Inverse shape design and identification of scatterers via geometric regularization and physics-embedded deep learning
• Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learning
• Predicting nonlinear optical scattering with physics-driven neural networks
• Data driven approaches in nanophotonics: A review of AI-enabled metadevices
• Auxiliary Physics-Informed Neural Networks for Forward, Inverse, and Coupled Radiative Transfer Problems
• Physics-consistent machine learning: output projection onto physical manifolds
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Integration of Programmable Diffraction with Digital Neural Networks
• Transfer Learning Assisted Fast Design Migration Over Technology Nodes: A Study on Transformer Matching Network
• Deep learning for nano-photonic materials -- The solution to everything!?
• Multiscale Physics-Informed Neural Networks for the Inverse Design of Hyperuniform Optical Materials
• Interpretable inverse-designed cavity for on-chip nonlinear and quantum optics
• Inverse design and experimental realization of plasma metamaterials
• Quasibound states in the continuum in photonic-crystal-based optomechanical microcavities
• Physics-guided hierarchical neural networks for Maxwell's equations in plasmonic metamaterials
• Optical neural network architecture for deep learning with the temporal synthetic dimension
• A precise bare simulation approach to the minimization of some distances. Foundations
• Inverse design of plasma metamaterial devices with realistic elements
• Roadmap on Integrated Quantum Photonics
• Analysis and design of transition radiation in layered uniaxial crystals using Tandem neural networks
• Multiplexed Supercell Metasurface Design and Optimization with Tandem Residual Networks
• A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems
• Deep learning for the modeling and inverse design of radiative heat transfer
• Layer-Resolved Quantum Transport in Twisted Bilayer Graphene: Counterflow and Machine Learning Predictions
• AI based design of 2D material integrated optical polarizers
• Fast approximate solvers for metamaterials design in electromagnetism
• A general framework for knowledge integration in machine learning for electromagnetic scattering using quasinormal modes
• Gradient-based optimization of scatterer arrangements based on the T-matrix method
• Towards a universal meta-optics solver via large language models
• Data-Efficient Electromagnetic Surrogate Solver Through Dissipative Relaxation Transfer Learning