A modified gradient descent strategy for computing neural networks solutions

DOI10.1016/J.CAM.2026.117949MaRDI QIDQ7316176zbMATH OpenFDO

Authors Jérôme Pousin

Publication date 19 August 2026

Published in Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.CAM.2026.117949

Mathematics Subject Classification ID

Numerical methods for partial differential equations, boundary value problems (65N99) Artificial neural networks and deep learning (68T07)

Cites work

• An overview on deep learning-based approximation methods for partial differential equations
• Deep learning
• Elliptic problems in nonsmooth domains
• Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
• scientific article; zbMATH DE number 3852340 (Why is no real title available?)
• scientific article; zbMATH DE number 1181255 (Why is no real title available?)
• Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
• Numerical optimization. Theoretical and practical aspects. Transl. from the French
• On the approximation by single hidden layer feedforward neural networks with fixed weights
• Some elliptic second order problems and neural network solutions: existence and error estimates
• Topological properties of the set of functions generated by neural networks of fixed size

This page was built for publication: A modified gradient descent strategy for computing neural networks solutions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7316176)