BriefGPT.xyz
Mar, 2024
SUPClust: 边界主动学习
SUPClust: Active Learning at the Boundaries
HTML
PDF
Yuta Ono, Till Aczel, Benjamin Estermann, Roger Wattenhofer
TL;DR
本研究提出了一种新的主动学习方法SUPClust，旨在识别类别之间的决策边界上的点，通过针对这些点收集最具信息性以优化模型对复杂决策区域的预测，实验证明标记这些点可以显著提高模型性能，即使在强类别不平衡的情况下。
Abstract
active learning
is a
machine learning
paradigm designed to optimize
model performance
in a setting where labeled data is expensive to acqu
→