BriefGPT.xyz
Jun, 2024
统一不确定性：将输入、数据和模型不确定性合并为单个公式
Unified Uncertainties: Combining Input, Data and Model Uncertainty into a Single Formulation
HTML
PDF
Matias Valdenegro-Toro, Ivo Pascal de Jong, Marco Zullich
TL;DR
通过神经网络传播输入不确定性时，我们提出了一种同时能够估计输入、数据和模型不确定性的方法，结果表明这种输入不确定性的传播导致更稳定的决策边界，即使在大量输入噪声的情况下也是如此。
Abstract
modelling uncertainty
in
machine learning models
is essential for achieving safe and reliable predictions. Most research on uncertainty focuses on output uncertainty (predictions), but minimal attention is paid t
→