Bayesian deep learning has always garnered substantial interest in the machine learning community.

This paper presents an innovative approach to classification tasks called Credal Deep Ensembles (CreDEs), ensembles of novel Credal-Set Neural Networks (CreNets), aiming to improve EU quantification in the framework of credal inference.

We compare the algorithms on a wide range of large, convolutional and transformer-based neural network architectures.

Neural networks are known toproduce poor uncertainty estimations, and avariety of approaches have been proposed to remedy this issue.

Although the ongoing success of deep learning is remarkable, the increasing data, model and training algorithm complexity makeathorough understanding oftheir inner workings increasingly difficult.

This is the appendix of the paper " Quantification of Uncertainty with Adversarial Models ". It consists of three sections.

Quantifying uncertainty is important for actionable predictions in real-world applications.