PulseAugur
中
实时 23:27:39
English(EN) Data-Efficient Neural Operator Training via Physics-Based Active Learning

基于物理的主动学习提高了神经算子训练效率

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员开发了一种名为基于物理的获取（physics-based acquisition）的新型主动学习技术，以提高训练神经算子以求解偏微分方程的效率。该方法利用方程的残差来智能地选择信息量最大的数据样本，从而减少了训练所需的总体数据量。在1D Burgers方程和2D可压缩Navier-Stokes方程上的实验表明，该方法优于随机获取，并在结合了基于物理的归纳偏置的同时，达到了最先进的数据效率。 AI

影响 提高了科学模拟中神经算子训练的数据效率，有可能加速依赖求解微分方程的领域的发现。

排序理由 该集群包含一篇详细介绍神经算子训练新方法的学术论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Han Wan, Rui Zhang, Hao Sun ·

    Spectral-inspired Operator Learning with Limited Data and Unknown Physics

    arXiv:2505.21573v3 Announce Type: replace-cross Abstract: Learning PDE dynamics from limited data with unknown physics is challenging. Existing neural PDE solvers either require large datasets or rely on known physics (e.g., PDE residuals or handcrafted stencils), leading to limi…

  2. arXiv cs.AI TIER_1 English(EN) · Alicja Polanska, Lorenzo Zanisi, Vignesh Gopakumar, Stanislas Pamela ·

    Data-Efficient Neural Operator Training via Physics-Based Active Learning

    arXiv:2605.21348v1 Announce Type: cross Abstract: Solving partial differential equations with neural operators significantly reduces computational costs but remains bottlenecked by high training data requirements. Active learning offers a natural framework to mitigate this by sel…

  3. arXiv cs.AI TIER_1 English(EN) · Stanislas Pamela ·

    Data-Efficient Neural Operator Training via Physics-Based Active Learning

    Solving partial differential equations with neural operators significantly reduces computational costs but remains bottlenecked by high training data requirements. Active learning offers a natural framework to mitigate this by selectively acquiring the most informative samples in…

相关实体

相关话题