English(EN) AdaptNTK: Adaptive Uncertainty Quantification and Active Learning for Neural Network Potentials

AdaptNTK框架提升了AI在分子动力学模拟中的应用

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

研究人员开发了AdaptNTK，一种用于神经网路势能不确定性量化和主动学习的新型框架。这种单一模型方法使用经验神经切线核（NTK）特征空间中的正则化马氏距离来估计不确定性，并且可以在不重新训练的情况下递归更新。AdaptNTK在分子动力学模拟中表现出强大的性能，与力误差实现了高相关性，并在rMD17和Transition-1X等数据集的主动学习实验中，尤其是在过渡态构型方面，优于集成方法。 AI

影响提高了AI驱动的分子动力学模拟的效率和可靠性，有望加速材料科学和药物发现。

排序理由该集群包含一篇研究论文，详细介绍了一种用于机器学习势能不确定性量化和主动学习的新方法。[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 →

本文如何被排名

Signal score: 29 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了一种用于机器学习势能不确定性量化和主动学习的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Prajwal Ananth, Shuwen Yue · 2026-09-02 04:00

AdaptNTK：神经网络势能的自适应不确定性量化与主动学习

arXiv:2609.00488v1 Announce Type: new Abstract: Machine learning interatomic potentials bridge the gap between quantum chemical precision and classical computational speed, enabling molecular dynamics simulations with first-principles accuracy. Their reliability is often improved…

本文如何被排名

报道来源 [1]

AdaptNTK：神经网络势能的自适应不确定性量化与主动学习

相关实体

相关话题