Regularization of inverse problems by neural networks

DOI10.1007/978-3-030-98661-2_81zbMATH Open1547.94042MaRDI QIDQ6606471

Linh Nguyen, Markus Haltmeier

Publication date: 16 September 2024

zbMATH Keywords

stabilityneural networksinverse problemsill-posednessdeep learningregularization theorytheoretical foundation

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Variational methods in imaging
• Big in Japan: regularizing networks for solving inverse problems
• Regularization by architecture: a deep prior approach for inverse problems
• On the complemented subspaces problem
• On linear transformations.
• Sparse regularization with l ^q penalty term
• Joint additive Kullback–Leibler residual minimization and regularization for linear inverse problems
• Inner, outer, and generalized inverses in banach and hilbert spaces
• Analysis of bounded variation penalty methods for ill-posed problems
• Solving ill-posed inverse problems using iterative deep neural networks
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Deep null space learning for inverse problems: convergence analysis and rates
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• NETT: solving inverse problems with deep neural networks
• Deep synthesis network for regularizing inverse problems
• Solving inverse problems using data-driven models
• Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography

This page was built for publication: Regularization of inverse problems by neural networks