Mapped Multi-Patch Spectral Extreme Learning Machine for Partial Differential Equations

DOI10.48550/arXiv.2609.31909MaRDI QIDQ7360700arXivFDO

Authors Yiran Wang, Suchuan Dong

Publication date 25 September 2026

Published in arXiv

Tldr We solve partial differential equations using mapped multi-patch Spectral Extreme Learning Machine (ELM), a fixed-feature method combining Chebyshev-Gauss-Lobatto differentiation matrices with ELM trial functions on curved domains.

Full work available at URL https://doi.org/10.48550/arXiv.2609.31909

arXiv classification

math.NA

Cites work

• A Nonoverlapping Domain Decomposition Method for Extreme Learning Machines: Elliptic Problems
• Bridging traditional and machine learning-based algorithms for solving PDEs: the random feature method
• Construction of curvilinear co-ordinate systems and applications to mesh generation
• Extreme learning machine: Theory and applications
• Local Extreme Learning Machines and Domain Decomposition for Solving Linear and Nonlinear Partial Differential Equations
• Local Randomized Neural Networks with Discontinuous Galerkin Methods for Partial Differential Equations
• Robust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint
• Subspace method based on neural networks for solving the partial differential equation

This page was built for publication: Mapped Multi-Patch Spectral Extreme Learning Machine for Partial Differential Equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7360700)