SwitchNet: A Neural Network Model for Forward and Inverse Scattering Problems

DOI10.1137/18M1222399zbMath1425.65208arXiv1810.09675OpenAlexW2981014499WikidataQ127020537 ScholiaQ127020537MaRDI QIDQ5240806

Lexing Ying, Yuehaw Khoo

Publication date: 29 October 2019

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1810.09675

zbMATH Keywords

inverse problemHelmholtz equationartificial neural networkoperator compression

Mathematics Subject Classification ID

Numerical methods for discrete and fast Fourier transforms (65T50) Numerical methods for integral transforms (65R10)

Related Items (41)

Meta-learning pseudo-differential operators with deep neural networks ⋮ Int-Deep: a deep learning initialized iterative method for nonlinear problems ⋮ Sampling type method combined with deep learning for inverse scattering with one incident wave ⋮ Using neural networks to accelerate the solution of the Boltzmann equation ⋮ Wide-Band Butterfly Network: Stable and Efficient Inversion Via Multi-Frequency Neural Networks ⋮ Robust Identification of Differential Equations by Numerical Techniques from a Single Set of Noisy Observation ⋮ Imaging conductivity from current density magnitude using neural networks* ⋮ Learning-based local weighted least squares for algebraic multigrid method ⋮ VI-DGP: a variational inference method with deep generative prior for solving high-dimensional inverse problems ⋮ Divide-and-conquer DNN approach for the inverse point source problem using a few single frequency measurements ⋮ Deep Ritz method with adaptive quadrature for linear elasticity ⋮ Predicting continuum breakdown with deep neural networks ⋮ Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation ⋮ MGIC: Multigrid-in-Channels Neural Network Architectures ⋮ Active learning based sampling for high-dimensional nonlinear partial differential equations ⋮ A direct sampling-based deep learning approach for inverse medium scattering problems ⋮ A Data-Assisted Two-Stage Method for the Inverse Random Source Problem ⋮ Application of neural networks to inverse elastic scattering problems with near-field measurements ⋮ A deep neural network-based method for solving obstacle problems ⋮ A neural network warm-start approach for the inverse acoustic obstacle scattering problem ⋮ Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics ⋮ A Reduced Order Schwarz Method for Nonlinear Multiscale Elliptic Equations Based on Two-Layer Neural Networks ⋮ Mathematical analysis and numerical methods for inverse scattering problems ⋮ Solving inverse problems with deep learning ⋮ On mathematical modeling in image reconstruction and beyond ⋮ Kernel methods are competitive for operator learning ⋮ Physical informed neural networks with soft and hard boundary constraints for solving advection-diffusion equations using Fourier expansions ⋮ An overview on deep learning-based approximation methods for partial differential equations ⋮ Solving traveltime tomography with deep learning ⋮ Learning nonlocal constitutive models with neural networks ⋮ Artificial neural network approximations of Cauchy inverse problem for linear PDEs ⋮ Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks ⋮ Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning ⋮ IDENT: identifying differential equations with numerical time evolution ⋮ Solving inverse problems using data-driven models ⋮ A neural network scheme for recovering scattering obstacles with limited phaseless far-field data ⋮ Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data ⋮ A non-gradient method for solving elliptic partial differential equations with deep neural networks ⋮ Efficient long-range convolutions for point clouds ⋮ Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning ⋮ Deep learning architectures for nonlinear operator functions and nonlinear inverse problems

Uses Software

• darch
• Keras
• Adam
• U-Net
• PDE-Net

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A perfectly matched layer for the absorption of electromagnetic waves
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Solving for high-dimensional committor functions using artificial neural networks
• The Mathematics of Computerized Tomography
• Reducing the Dimensionality of Data with Neural Networks
• Inverse scattering problems with multi-frequencies
• Sparse Fourier Transform via Butterfly Algorithm
• MUSIC for Extended Scatterers as an Instance of the Factorization Method
• A Fast Butterfly Algorithm for the Computation of Fourier Integral Operators
• Solving the quantum many-body problem with artificial neural networks
• Approximate Separability of the Green's Function of the Helmholtz Equation in the High Frequency Limit
• Solving high-dimensional partial differential equations using deep learning
• Deep Potential: A General Representation of a Many-Body Potential Energy Surface
• A Multiscale Neural Network Based on Hierarchical Matrices
• Butterfly Factorization
• High Resolution Inverse Scattering in Two Dimensions Using Recursive Linearization
• Interpolative Butterfly Factorization
• Inverse acoustic and electromagnetic scattering theory

This page was built for publication: SwitchNet: A Neural Network Model for Forward and Inverse Scattering Problems