Transformers as neural operators for solutions of differential equations with finite regularity

DOI10.1016/j.cma.2024.117560MaRDI QIDQ6669055

Ahmad Peyvan, Zhongqiang Zhang, George Em. Karniadakis, Benjamin Shih

Publication date: 22 January 2025

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

zbMATH Keywords

Riemann problemsoperator learningneural operatorstempered fractional neuron models

Mathematics Subject Classification ID

Biology and other natural sciences (92-XX) Partial differential equations (35-XX)

Cites Work

• Unnamed Item
• On numerical approximations of fractional-order spiking neuron models
• A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data
• SVD perspectives for augmenting DeepONet flexibility and interpretability
• Local approximation of operators
• Front tracking for hyperbolic conservation laws
• Transformers for modeling physical systems
• Mesh-informed neural networks for operator learning in finite element spaces
• A corrected \(\mathrm{L}1\) method for a time-fractional subdiffusion equation
• Convergence rate of DeepONets for learning operators arising from advection-diffusion equations
• Mitigating spectral bias for the multiscale operator learning with hierarchical attention
• RiemannONets: interpretable neural operators for Riemann problems

This page was built for publication: Transformers as neural operators for solutions of differential equations with finite regularity