PulseAugur
实时 11:03:50
English(EN) Tubular Neighbourhoods of Pfaffian Sets and Applications to Neural Networks

新的数学界限应用于神经网络鲁棒性

研究人员发表了一篇论文,详细介绍了光滑Pfaffian超曲面管状邻域体积的新数学界限。这些界限使用定义函数的Pfaffian格式表示,可用于理解神经网络分类器的鲁棒性。具体而言,该研究为采用Pfaffian激活函数的神经网络的条件数提供了尾部界限,并推导出了具有有理权重的单隐藏层sigmoid网络中决策边界的宽度多项式界限。 AI

影响 为分析神经网络分类器的鲁棒性提供了理论基础。

排序理由 该集群包含一篇在arXiv上发表的学术论文。

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 →

新的数学界限应用于神经网络鲁棒性

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Paul Lezeau, Martin Lotz ·

    Tubular Neighbourhoods of Pfaffian Sets and Applications to Neural Networks

    arXiv:2607.08370v1 Announce Type: cross Abstract: We derive bounds for the volume of tubular neighbourhoods of smooth Pfaffian hypersurfaces, generalising known results for algebraic varieties. The bounds are given in terms of the Pfaffian format of the defining functions. As an …

  2. arXiv cs.LG TIER_1 English(EN) · Martin Lotz ·

    Tubular Neighbourhoods of Pfaffian Sets and Applications to Neural Networks

    We derive bounds for the volume of tubular neighbourhoods of smooth Pfaffian hypersurfaces, generalising known results for algebraic varieties. The bounds are given in terms of the Pfaffian format of the defining functions. As an application, we obtain tail bounds on the probabil…