Epistemic Wrapping for Uncertainty Quantification
This work addresses the problem of improving model robustness and reliability for machine learning practitioners, though it appears incremental as it builds on existing Bayesian Neural Networks.
The paper tackled uncertainty estimation in classification by introducing Epistemic Wrapping, which transforms Bayesian Neural Network outputs into belief function posteriors, resulting in significant enhancements in generalization and uncertainty quantification across multiple datasets like MNIST and CIFAR.
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.