用信念函数提升分类模型的不确定性估计能力。
Epistemic Wrapping for Uncertainty Quantification
- 将贝叶斯神经网络输出转为信念函数后验，捕捉认知不确定性。
- 在多个数据集上显著提升泛化能力和不确定性量化效果。
- 方法通用高效，适合对可靠性要求高的实际应用。
不确定性估计在机器学习中至关重要，尤其在分类任务中可提升模型的鲁棒性与可靠性。本文提出一种名为「认知封装」（Epistemic Wrapping）的新方法，以贝叶斯神经网络（BNN）为基础，将其输出转化为信念函数后验，有效捕捉认知不确定性，提供一种高效且通用的不确定性量化途径。在MNIST、Fashion-MNIST、CIFAR-10和CIFAR-100数据集上的实验表明，该方法结合贝叶斯神经网络与区间神经网络进行推理，显著提升了模型的泛化性能与不确定性估计质量。
原文摘要 · Abstract (English)
Uncertainty estimation is pivotal in machine learning, especially for classification tasks, as it improves the robustness and reliability of models. We introduce a novel `Epistemic Wrapping' methodology aimed at improving uncertainty estimation in classification. Our approach uses Bayesian Neural Networks (BNNs) as a baseline and transforms their outputs into belief function posteriors, effectively capturing epistemic uncertainty and offering an efficient and general methodology for uncertainty quantification. Comprehensive experiments employing a Bayesian Neural Network (BNN) baseline and an Interval Neural Network for inference on the MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 datasets demonstrate that our Epistemic Wrapper significantly enhances generalisation and uncertainty quantification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。