56 citations · 56 across the 3 of their papers we have counts for
3 papers
cs.LG2024
Epistemic Uncertainty Quantification For Pre-trained Neural Network
Hanjing Wang, Qiang Ji
Epistemic uncertainty quantification (UQ) identifies where models lack knowledge. Traditional UQ methods, often based on Bayesian neural networks, are not suitable for pre-trained…
cs.LG2023
Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning
Hanjing Wang, Dhiraj Joshi, Shiqiang Wang +1
Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critica…
cs.AI2012★ 56 cited
Strategy Selection in Influence Diagrams using Imprecise Probabilities
Cassio Polpo de Campos, Qiang Ji
This paper describes a new algorithm to solve the decision making problem in Influence Diagrams based on algorithms for credal networks. Decision nodes are associated to imprecise…