English(EN) Grassmann--Pl\"ucker Parametrization of Convolutional Filter Subspaces: Regularity and Closed Embeddings

新的几何方法对神经网络中的卷积滤波器进行参数化

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

研究人员开发了一种新颖的几何方法来参数化神经网络中的卷积滤波器。该方法将滤波器表示为滤波器空间内的固定维子空间，而不是单个向量。这项工作使用Grassmannian几何建立了射影参数化，证明该映射是一个闭合嵌入，并产生一个光滑的射影神经网络簇。研究还探讨了与滤波器冗余和低秩卷积的潜在联系，尽管应用提案需要进一步的数值验证。 AI

影响引入了一个新的数学框架，用于理解和潜在地优化卷积神经网络滤波器。

排序理由该集群包含一篇学术论文，详细介绍了神经网络组件的新数学框架。[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: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了神经网络组件的新数学框架。[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, model release; 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) · Hongyu Yuan, Huaiqing Zuo · 2026-09-04 04:00

Grassmann--Pl"ucker 参数化卷积滤波器子空间：正则性和闭嵌入

arXiv:2609.03361v1 Announce Type: cross Abstract: We propose a geometric parametrization of the filters in a single convolutional layer: the parameter is no longer an ordered family of filter vectors, but a fixed-dimensional subspace of the filter space. For one-dimensional finit…

本文如何被排名

报道来源 [1]

Grassmann--Pl"ucker 参数化卷积滤波器子空间：正则性和闭嵌入

相关实体

相关话题