neural tangent kernel 1partial differential equations 1physics-informed neural networks 1residual weighting 1training priority 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Multi-dimensional training-priority weighting based on physical information propagation paths: a unified residual-weighting framework for physics-informed neural networks
Zhangyi Lian, Xinda Dong, Wenxuan Huo +4
The paper proposes a unified framework that assigns priority-based weights to residuals in physics-informed neural networks, aligning training with the natural physical information…
cs.LG2025
Over-PINNs: Enhancing Physics-Informed Neural Networks via Higher-Order Partial Derivative Overdetermination of PDEs
Wenxuan Huo, Qiang He, Gang Zhu +1
Partial differential equations (PDEs) serve as the cornerstone of mathematical physics. In recent years, Physics-Informed Neural Networks (PINNs) have significantly reduced the dep…