Be Bayesian by Attachments to Catch More Uncertainty

arXiv:2310.13027v2 Announce Type: replace
Abstract: Bayesian Neural Networks (BNNs) have become one of the promising approaches for uncertainty estimation due to the solid theorical foundations. However, the performance of BNNs is affected by the ability of catching uncertainty. Instead of only seeking the distribution of neural network weights by in-distribution (ID) data, in this paper, we propose a new Bayesian Neural Network with an Attached structure (ABNN) to catch more uncertainty from out-of-distribution (OOD) data. We first construct a mathematical …

abstract arxiv bayesian become cs.ai cs.lg data distribution however network networks neural network neural networks performance solid type uncertainty