BriefGPT.xyz
Apr, 2024
用适当评分规则量化随机和知识不确定性
Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rules
HTML
PDF
Paul Hofman, Yusuf Sale, Eyke Hüllermeier
TL;DR
提出了基于合适评分规则（proper scoring rules）的新的测量方法，用于量化机器学习中的系统不确定性和认知不确定性，建立了不同不确定性表示之间的联系，并引入了新的认知和系统不确定性度量。
Abstract
uncertainty representation
and
quantification
are paramount in
machine learning
and constitute an important prerequisite for safety-critic
→