Wide-band butterfly network: stable and efficient inversion via multi-frequency neural networks
Preprint
Abstract
We introduce an end-to-end deep learning architecture called the wide-band butterfly network (WideBNet) for approximating the inverse scattering map from wide-band scattering data. This architecture incorporates tools from computational harmonic analysis, such as the butterfly factorization, and traditional multi-scale methods, such as the Cooley-Tukey FFT algorithm, to drastically reduce the number of trainable parameters to match the inherent complexity of the problem. As a result WideBNet is efficient: it requires fewer training points than off-the-shelf architectures, and has stable training dynamics, thus it can rely on standard weight initialization strategies. The architecture automatically adapts to the dimensions of the data with only a few hyper-parameters that the user must specify. WideBNet is able to produce images that are competitive with optimization-based approaches, but at a fraction of the cost, and we also demonstrate numerically that it learns to super-resolve scatterers in the full aperture scattering setup.Keywords
All Related Versions
This publication has 65 references indexed in Scilit:
- Solving Traveltime Tomography with Deep LearningCommunications in Mathematics and Statistics, 2023
- Travel Time TomographyActa Mathematica Sinica, English Series, 2019
- A multiscale neural network based on hierarchical nested basesResearch in the Mathematical Sciences, 2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Super-Resolution from Noisy DataJournal of Fourier Analysis and Applications, 2013
- Towards a Mathematical Theory of Super‐resolutionCommunications on Pure and Applied Mathematics, 2013
- Inverse Acoustic and Electromagnetic Scattering Theory2013
- An algorithm for the rapid evaluation of special function transformsApplied and Computational Harmonic Analysis, 2010
- A perfectly matched layer for the absorption of electromagnetic wavesJournal of Computational Physics, 1994
- Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networksNeural Networks, 1990