mlsanityData to 14 Oct 2026

Neural Born Iteration Method For Solving Inverse Scattering Problems: 2D Cases

arXiv 2112.09831 ↗First posted 18 Dec 2021physics.comp-ph cs.AI eess.IVcited by 9

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose the neural Born iterative method (NeuralBIM) for solving 2D inverse scattering problems (ISPs) by drawing on the scheme of physics-informed supervised residual learning (PhiSRL) to emulate the computing process of the traditional Born iterative method (TBIM). NeuralBIM employs independent convolutional neural networks (CNNs) to learn the alternate update rules of two different candidate solutions regarding the residuals. Two different schemes are presented in this paper, including the supervised and unsupervised learning schemes. With the data set generated by the method of moments (MoM), supervised NeuralBIM are trained with the knowledge of total fields and contrasts. Unsupervised NeuralBIM is guided by the physics-embedded objective function founding on the governing equations of ISPs, which results in no requirement of total fields and contrasts for training. Numerical and experimental results further validate the efficacy of NeuralBIM.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 9 of its 51 references that are in the map. First posted on arXiv 18 Dec 2021.

Builds on

9 of 51 references.

References · 9

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  3. 2017Stable Architectures for Deep Neural Networkscited by 341
  4. 2017PDE-Net: Learning PDEs from Datacited by 311
  5. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
  6. 2018Deep Neural Networks Motivated by Partial Differential Equationscited by 187
  7. 2018Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networkscited by 176
  8. 2018DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scatteringcited by 31
  9. 2018Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Functioncited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 3; 2026: 2.

9 papers.

  1. 2022Physics Embedded Machine Learning for Electromagnetic Data Imagingcited by 11
  2. 2025Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problemscited by 5
  3. 2023Deep Injective Prior for Inverse Scatteringcited by 3
  4. 2024Multi-frequency Neural Born Iterative Method for Solving 2-D Inverse Scattering Problemscited by 2
  5. 2025Improved Physics-Driven Neural Network to Solve Inverse Scattering Problemscited by 2
  6. 2024VBIM-Net: Variational Born Iterative Network for Inverse Scattering Problemscited by 1
  7. 2025A Differentiable Framework for Full and Phaseless Data Inversion Using Neural Implicit Contrast-Source Representationcited by 1
  8. 2026Coordinate-Residual Physics-Driven Neural Network for Inverse Scattering Imagingcited by 0
  9. 2026Structured Multi-Level-Set Inversion for 3-D Electromagnetic Inverse Scatteringcited by 0