PulseAugur
实时 07:20:45
English(EN) Multi-dimensional training-priority weighting based on physical information propagation paths: a unified residual-weighting framework for physics-informed neural networks

新框架通过信息传播路径增强物理信息神经网络

研究人员开发了一种新的物理信息神经网络(PINNs)框架,解决了这些网络在处理偏微分方程方面的局限性。提出的多维度训练优先级加权系统考虑了信息的物理传播,优先从源区域到依赖区域在空间、时间、边界维度上进行学习。该方法通过神经切线核动力学进行分析,旨在通过使网络的学习过程与物理原理保持一致来提高训练稳定性和预测精度,在不改变网络架构的情况下,在基准案例上持续改进。 AI

影响 提高了用于求解复杂物理模拟的神经网络的准确性和稳定性。

排序理由 关于物理信息神经网络新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新框架通过信息传播路径增强物理信息神经网络

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Zhangyi Lian, Xinda Dong, Wenxuan Huo, Weifeng Huang, Gang Zhu, Qiang He ·

    Multi-dimensional training-priority weighting based on physical information propagation paths: a unified residual-weighting framework for physics-informed neural networks

    arXiv:2607.11094v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have shown promise for solving partial differential equations (PDEs); however, their synchronous optimization treats residuals of different regions and constraints equally, which is inconsist…