Big in Japan: regularizing networks for solving inverse problems

DOI10.1007/S10851-019-00911-1zbMath1434.68525DBLPjournals/jmiv/SchwabAH20arXiv1812.00965OpenAlexW2902695846WikidataQ92058818 ScholiaQ92058818MaRDI QIDQ1988359

Markus Haltmeier, Stephan Antholzer, Johannes Schwab

Publication date: 23 April 2020

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1812.00965

zbMATH Keywords

convergence analysisconvergence ratesinverse problemsconvolutional neural networksnull space networksregularizing networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Systems of nonsingular linear integral equations (45F05) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Numerical solution to inverse problems in abstract spaces (65J22)

Related Items (1)

Data-consistent neural networks for solving nonlinear inverse problems

Uses Software

• U-Net
• NETT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Variational methods in imaging
• Solving ill-posed inverse problems using iterative deep neural networks
• Deep null space learning for inverse problems: convergence analysis and rates
• Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems
• Deep learning for photoacoustic tomography from sparse data
• NETT: solving inverse problems with deep neural networks
• Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography
• Convergence rates for Tikhonov regularization based on range inclusions

This page was built for publication: Big in Japan: regularizing networks for solving inverse problems