English(EN) Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations

论文分析浮点神经网络的表达能力

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-27 16:30

研究人员发表了一篇论文，探讨了使用浮点算术运算的神经网络的表达能力，超越了假设精确实数的理论模型。该研究引入了一个框架来分析任意归约顺序和不精确激活实现如何影响网络的函数表示能力。这项工作确立了浮点神经网络能够实现通用表示的条件，将先前的发现扩展到更广泛的实际激活函数。 AI

影响这项研究为在实际的、有限精度环境中神经网络的行为提供了更现实的理论理解。

排序理由该集群包含一篇在arXiv上发表的研究论文，详细介绍了神经网络表达能力的理论进展。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 该集群包含一篇在arXiv上发表的研究论文，详细介绍了神经网络表达能力的理论进展。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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: 134 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Yeachan Park, Geonho Hwang, Wonyeol Lee, Sejun Park · 2026-05-28 04:00

具有任意归约顺序和不精确激活实现的浮点神经网络的表达能力

arXiv:2605.28704v1 Announce Type: new Abstract: Most existing expressivity theories for neural networks assume exact real arithmetic, whereas practical neural networks are executed under finite-precision floating-point arithmetic with implementation-dependent execution semantics.…
arXiv cs.LG TIER_1 English(EN) · Sejun Park · 2026-05-27 16:30

具有任意归约顺序和不精确激活实现的浮点神经网络的表达能力

Most existing expressivity theories for neural networks assume exact real arithmetic, whereas practical neural networks are executed under finite-precision floating-point arithmetic with implementation-dependent execution semantics. Recent works have begun studying the expressive…