研究人员推出了一种新颖的、受物理学启发的特征选择方法——基于噪声的光谱嵌入（NBSE），用于处理高维数据集。该技术通过构建相似性图并识别临界西森温度来揭示冗余或相关的维度，从而避免了贪婪搜索。在ImageNet嵌入上的实验表明，NBSE可以在保持高分类精度的同时显著压缩特征，其性能优于其他选择方法。 AI
影响 为深度学习模型提供了一种新的高效特征选择方法，有望降低计算成本并提高压缩模型的性能。
排序理由 介绍新特征选择方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2604.24692v1 Announce Type: new Abstract: We propose Noise-Based Spectral Embedding (NBSE), a physics-informed framework for selecting informative features from high-dimensional data without greedy search. NBSE constructs a sparse similarity graph on the samples and identif…
We propose Noise-Based Spectral Embedding (NBSE), a physics-informed framework for selecting informative features from high-dimensional data without greedy search. NBSE constructs a sparse similarity graph on the samples and identifies the Nishimori temperature $β_N$ the critical…
We propose Noise-Based Spectral Embedding (NBSE), a physics-informed framework for selecting informative features from high-dimensional data without greedy search. NBSE constructs a sparse similarity graph on the samples and identifies the Nishimori temperature $β_N$ the critical…