新的Prime Fourier Embeddings为神经网络保留代数结构

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-15 04:00

研究人员推出了一种新颖的整数编码方法Prime Fourier Embeddings (PFE)，该方法能够为神经网络保留其代数结构。该方法利用源自谐波分析的素数索引（cos, sin）对，通过选择相关的素数通道而非推断结构来处理模运算。实证研究证实，PFE在任务相关通道和无关通道之间实现了高专业化比率，在无平方因子复合模数上达到了完美的分布内测试准确率。 AI

影响引入了一种新颖的嵌入技术，可以改善神经网络处理结构化数值数据的方式。

排序理由研究论文，详细介绍了一种用于神经网络的新嵌入技术。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了一种用于神经网络的新嵌入技术。[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: 77 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。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Hyunsang Hwang, Suhyun Bae, Donghun Lee · 2026-07-15 04:00

Prime Fourier Embeddings: A Principled Basis for Modular Arithmetic

arXiv:2606.23044v2 Announce Type: replace-cross Abstract: Numbers have algebraic structure that standard neural embeddings often fail to expose. We introduce Prime Fourier Embeddings (PFE), which encode integers as prime-indexed (cos, sin) pairs derived from the harmonic analysis…

本文如何被排名

报道来源 [1]

Prime Fourier Embeddings: A Principled Basis for Modular Arithmetic

相关实体

相关话题