发表机构
IU International University of Applied Sciences(IU国际应用科学大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
针对LOSO评估下NAS计算昂贵的问题,提出无泄漏的基于块的共享方法,在BioVid数据集上提升准确率并大幅减少参数。
AI 中文摘要
留一受试者(LOSO)评估可估计基于受试者的分类的泛化性能,但会使神经架构搜索(NAS)在计算上变得昂贵,因为完全嵌套的实现需要N次独立的架构搜索,并假设训练成本近似线性,其复杂度为O(N^2)。我们提出了一种无泄漏的、基于块的方法,在受试者之间共享NAS运行。在BioVid热痛数据集上,我们的方法将平均准确率从82.79%提高到83.39%,同时将参数数量减少了最多99.2%。
英文摘要
Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS) computationally expensive because a fully nested implementation requires N independent architecture searches and, assuming approximately linear training cost, scales as O(N^2). We propose a leakage-free, block-based approach that shares NAS runs across subjects. On the BioVid Heat Pain dataset, our approach increased the mean accuracy from 82.79% to 83.39% while reducing the number of parameters by up to 99.2%.