English(EN) Neuron merging via inverse-activation regression for post-training compression of sigmoid neural networks

用于压缩Sigmoid神经网络的新神经元合并技术

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-05 04:00

研究人员开发了用于压缩已训练神经网络的新方法，重点关注Sigmoid网络。所提出的技术涉及神经元聚类和基于其响应的合并。一种方法使用无数据贡献加权平均，另一种方法通过逆激活函数将神经元响应映射回预激活空间，利用最小二乘法估计代表性神经元权重和偏置。研究了数据辅助和无数据策略，研究结果表明权重信息对于聚类至关重要，而激活信息是合并过程中代表性神经元重建的关键。 AI

影响引入了新颖的模型压缩技术，有可能在资源受限的设备上更有效地部署神经网络。

排序理由这是一篇详细介绍神经网络压缩新方法的学术论文。[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: 6 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍神经网络压缩新方法的学术论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Ao Kuniya, Jun Ohkubo · 2026-10-05 04:00

通过逆激活回归实现神经元合并以对 Sigmoid 神经网络进行训练后压缩

arXiv:2610.02559v1 Announce Type: new Abstract: As neural networks continue to grow in scale, model compression is becoming increasingly important for efficient inference under limited computational resources. Structured pruning methods remove neurons or channels that are estimat…

本文如何被排名

报道来源 [1]

通过逆激活回归实现神经元合并以对 Sigmoid 神经网络进行训练后压缩

相关实体

相关话题