Quadratic Neural Networks for Solving Inverse Problems

DOI10.1080/01630563.2024.2316580MaRDI QIDQ6193984zbMATH OpenFDO

Authors Leon Frischauf, Otmar Scherzer, Cong Shi

Publication date 19 March 2024

Published in Numerical Functional Analysis and Optimization (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2401.09445

zbMATH Keywords

generalized neural network functionsinverse problems

Mathematics Subject Classification ID

Numerical solutions to overdetermined systems, pseudoinverses (65F20) Numerical solution to inverse problems in abstract spaces (65J22) Numerical optimization and variational techniques (65K10) Artificial neural networks and deep learning (68T07)

Recommendations

• Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
• NETT: solving inverse problems with deep neural networks
• Big in Japan: regularizing networks for solving inverse problems
• Convolutional Neural Networks in Phase Space and Inverse Problems
• Gauss-Newton method for solving linear inverse problems with neural network coders

Cites work

• Approximation and learning by greedy algorithms
• Approximation by superpositions of a sigmoidal function
• Approximation properties of a multilayered feedforward artificial neural network
• Characterization of the variation spaces corresponding to shallow neural networks
• Deep distributed convolutional neural networks: universality
• Deep synthesis network for regularizing inverse problems
• Gauss-Newton method for solving linear inverse problems with neural network coders
• Harmonic analysis on spaces of homogeneous type. With a preface by Yves Meyer
• scientific article; zbMATH DE number 3112450 (Why is no real title available?)
• scientific article; zbMATH DE number 52869 (Why is no real title available?)
• scientific article; zbMATH DE number 3506596 (Why is no real title available?)
• scientific article; zbMATH DE number 1174614 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• scientific article; zbMATH DE number 7625172 (Why is no real title available?)
• Learning with recurrent neural networks
• Multilayer feedforward networks are universal approximators
• Provable approximation properties for deep neural networks
• Radial Basis Functions
• Regularisierung schlecht gestellter Probleme durch Projektionsverfahren
• Ten Lectures on Wavelets
• Universal approximation bounds for superpositions of a sigmoidal function
• Universal approximation with quadratic deep networks
• Universality of deep convolutional neural networks

Cited in

(2)

• Solving inverse problems of obtaining super-resolution using neural networks
• Provable wavelet-based neural approximation

This page was built for publication: Quadratic Neural Networks for Solving Inverse Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6193984)