Epistemic Deep Learning. (arXiv:2206.07609v1 [cs.LG])

Web: http://arxiv.org/abs/2206.07609

The belief function approach to uncertainty quantification as proposed in the
Demspter-Shafer theory of evidence is established upon the general mathematical
models for set-valued observations, called random sets. Set-valued predictions
are the most natural representations of uncertainty in machine learning. In
this paper, we introduce a concept called epistemic deep learning based on the
random-set interpretation of belief functions to model epistemic learning in
deep neural networks. We propose a novel random-set convolutional neural
network for classification that produces scores …

arxiv deep deep learning learning lg