Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs
arXiv 于 2026 年 11 月发布了论文《Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs》(编号 2611.18409v1),该论文提出将有限元方法与物理信息神经网络(PINN)结合,用于非线性偏微分方程的大规模并行模拟。论文摘要指出,近年来将 PINN 应用于 PDE 建模的研究已取得显著进展。同一批次中另有两篇相关 arXiv 新论文,分别涉及深度 Bernstein 神经网络的反向可达性验证(2611.22083v1)与基于积分物理信息神经网络的高阶交互重建(2611.21935v1)。目前这些论文均以摘要形式公布,具体方法与实验结果尚未在材料中披露。
How this story unfolded
Key points7 items Model summary · ordered by when the evidence was published
- Point 01 11/16, 13:00
arXiv 发布编号 2611.18409v1 的新论文,题为 Fuse-PINN。
Based on 1 - Point 02 11/16, 13:00
Fuse-PINN 将有限元方法与物理信息神经网络结合,用于非线性 PDE 的大规模并行模拟。
Based on 1 - Point 03 11/16, 13:00
论文摘要称,PINN 应用于 PDE 建模的研究近年已取得显著进展。
Based on 1 - Point 04 11/18, 13:00
同批 arXiv 新论文 2611.22083v1 研究深度 Bernstein 神经网络的反向可达性验证。
Based on 1 - Point 05 11/18, 13:00
该验证工作强调以数学上严谨的方式确保复杂神经网络系统的安全。
Based on 1 - Point 06 11/18, 13:00
同批 arXiv 新论文 2611.21935v1 提出用积分物理信息神经网络重建高阶交互。
Based on 1 - Point 07 11/18, 13:00
高阶交互重建被描述为复杂网络系统研究中的基础性挑战。
Based on 1
ReportsBy publish time · newer further down
- November 16, 2026 · Mon
- Start
Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs
Original summary arXiv:2611.18409v1 Announce Type: new Abstract: Research in the domain of Physics-Informed Neural Networks applied to PDE modelling has advanced significantly in recent years, prov
arXiv cs.LG Original ↗ - November 18, 2026 · Wed
- +2d 0h
Higher-Order Interaction Reconstruction via Integral Physics-Informed Neural Networks
Original summary arXiv:2611.21935v1 Announce Type: new Abstract: Reconstructing higher-order interactions is a fundamental challenge in complex networked systems, with applications in ecological, s
arXiv cs.LG Original ↗ - +2d 0h
BernBRS: Certified Backward Reachability for Deep Bernstein Neural Networks
Original summary arXiv:2611.22083v1 Announce Type: new Abstract: Ensuring the safety of complex neural network systems requires mathematically rigorous verification. While backward reachability ana
arXiv cs.LG Original ↗ - Still developing · later reports will keep extending this axis