English(EN) Learnable Spectral Activations

新方法可学习谱激活改进神经网络表示

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-07 04:00

研究人员推出了一种新颖的隐式神经表示（INR）方法——可学习谱激活（LSA）。LSA用截断的傅里叶级数残差替换固定的非线性，允许在训练期间学习谐波幅度。该方法通过将线性权重选择与频谱整形分离开来，优化了表示的分解，从而在音频、图像和神经场等各种任务中提高了优化和重建质量。 AI

影响这项研究可能导致在各个领域更高效、更有效的神经网络训练和重建。

排序理由该集群描述了一篇发表在arXiv上的新研究论文，其中详细介绍了一种新颖的神经网络方法。[lever_c_demoted from research: ic=1 ai=1.0]

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: 19 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇发表在arXiv上的新研究论文，其中详细介绍了一种新颖的神经网络方法。[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, 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。

arXiv cs.LG TIER_1 English(EN) · Tamir Shor, Or Litany, Alex Bronstein · 2026-10-07 04:00

可学习谱激活

arXiv:2610.07419v1 Announce Type: new Abstract: Implicit neural representations (INRs) are shaped by the spectral structure induced by their input encodings and activation functions. Existing methods improve fitting primarily by modifying which frequencies are available to the ne…