研究人员开发了一个名为 Cut-DeepONet 的新框架，以改进神经算子在处理偏微分方程中的不连续性和尖锐过渡的方式。该方法将域划分为平滑区域，并在更高维度的空间中表示不连续性，从而避免直接近似。实验表明，Cut-DeepONet 通过使用更少的参数和改变问题的表示方式，即使在低分辨率数据下也优于现有方法。 AI
影响 增强了神经网络模拟具有尖锐过渡的复杂物理现象的能力。
排序理由 该集群包含一篇详细介绍神经算子新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.19823v1 Announce Type: cross Abstract: Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently continuous representations struggle to capture discontinuities and sharp transitions. …
Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently continuous representations struggle to capture discontinuities and sharp transitions. Existing approaches typically approximate such fea…