English(EN) An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks

新框架提升物理信息神经网络精度

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-02 14:03

研究人员开发了 DSGNAR，一个旨在改进物理信息神经网络 (PINNs) 训练的新型优化框架。该框架解决了以往限制 PINNs 精度（相比经典求解器）的病态问题。DSGNAR 在包括 Burgers 方程和高维 Poisson 问题在内的各种问题上实现了显著改进，达到了极低的误差率，同时还展示了更快的计算速度。 AI

影响该框架有望显著提高复杂物理系统仿真的准确性和速度，造福科学研究和工程应用。

排序理由该条目是一篇学术论文，详细介绍了一种针对特定类型神经网络的新优化框架。[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 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Joseph Webb, Sadok Jerad, Coralia Cartis · 2026-07-03 04:00

An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks

arXiv:2607.02194v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations, yet they have struggled to reach the precision of classical solvers. The obstacle is increasingly understood to be o…
arXiv cs.LG TIER_1 English(EN) · Coralia Cartis · 2026-07-02 14:03

An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks

Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations, yet they have struggled to reach the precision of classical solvers. The obstacle is increasingly understood to be one of optimisation, owing to the severely ill-co…

报道来源 [2]

An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks

An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks

相关实体

相关话题