English(EN) Spectral Stability of Pseudoinverse-Based Extreme Learning Machine

研究论文分析伪逆型极限学习机的谱稳定性

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-09 15:15

本研究论文探讨了使用伪逆方法计算输出权重的极限学习机（ELMs）的谱稳定性。研究表明，隐藏层矩阵的最小奇异值是放大输出权重扰动的关键因素，而条件数则量化了隐藏层的instability。奇异值分解（SVD）伪逆计算与迭代超幂法之间的比较表明，SVD方法在病态条件下提供了更好的可靠性。 AI

影响为特定机器学习训练方法的数值稳定性提供了理论见解。

排序理由该集群包含一篇在arXiv上发表的学术论文。

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

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Bich Van Nguyen, Ngoc Anh Khong · 2026-07-10 04:00

Spectral Stability of Pseudoinverse-Based Extreme Learning Machine

arXiv:2607.08581v1 Announce Type: new Abstract: Extreme Learning Machine (ELM) computes output weights analytically using the Moore-Penrose pseudoinverse. Although this leads to fast training, its numerical stability depends strongly on the conditioning of the hidden layer matrix…
arXiv cs.LG TIER_1 English(EN) · Ngoc Anh Khong · 2026-07-09 15:15

Spectral Stability of Pseudoinverse-Based Extreme Learning Machine

Extreme Learning Machine (ELM) computes output weights analytically using the Moore-Penrose pseudoinverse. Although this leads to fast training, its numerical stability depends strongly on the conditioning of the hidden layer matrix. This paper studies pseudoinverse-based ELM fro…