Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks

arXiv:2403.08652v1 Announce Type: new
Abstract: Deep Neural Networks (DNNs) do not inherently compute or exhibit empirically-justified task confidence. In mission critical applications, it is important to both understand associated DNN reasoning and its supporting evidence. In this paper, we propose a novel Bayesian approach to extract explanations, justifications, and uncertainty estimates from DNNs. Our approach is efficient both in terms of memory and computation, and can be applied to any black box DNN without any retraining, including applications to anomaly …

abstract applications arxiv bayesian box compute confidence cs.lg dnn evidence extract mission mission critical networks neural networks novel paper reasoning stat.ml type uncertainty