深度学习预测中认知不确定性的来源追踪：同方差与异方差线性化估计器
Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators
AI总结：
本研究将两类经典统计估计器适配深度学习，借助近似Fisher信息矩阵追踪认知不确定性的来源，实验验证其可区分测试点受不确定性来源的差异，能提升实际应用的鲁棒性。
AI中文摘要：
我们将两种用于量化不确定性的经典统计估计器适配到现代深度学习中，以更清晰地阐明由两类来源导致的不确定性：随机不确定性或局部数据稀缺。该方法利用近期近似Fisher信息矩阵的进展，使其可扩展至实际架构。实验结果表明，每个测试点受两类来源的影响存在差异，凸显了本估计器在提升现实应用鲁棒性方面的实用价值。
英文摘要：
We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources : aleatoric uncertainty, or locally scarce data. Our approach leverages recent advances in approximate Fisher Information Matrices, to enable scaling to actual architectures. Experimental results demonstrate how each test points is differentially impacted by both sources, highlighting the practical utility of our estimators in improving the robustness of real-world applications.
