一篇新论文探讨了物理信息神经网络 (PINNs) 在微分几何问题中的应用。研究提出，通过将几何构造表述为微分泛函的最小化，这些泛函可以转化为神经网络的损失函数。这种方法将 AI 的损失最小化目标与解决复杂几何问题的目标相统一。 AI
影响 通过将微分几何中的复杂问题重新表述为损失函数，展示了神经网络解决这些问题的 novel 应用。
排序理由 这是一篇发表在 arXiv 上的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
PINNs 利用微分几何进行 AI 损失最小化在新研究中
报道来源 [2]
-
PINNs in More General Geometry
arXiv:2604.25020v1 Announce Type: cross Abstract: Neural architectures trained with losses inspired by differential conditions are the basis for PINN models. Since many constructions in differential geometry may be framed as minimisation of a differential functional, these functi…
-
PINNs in More General Geometry
Neural architectures trained with losses inspired by differential conditions are the basis for PINN models. Since many constructions in differential geometry may be framed as minimisation of a differential functional, these functionals can be coded as loss functions to align the …