Formalizes explanation distributions from BNNs via push-forward measures and proposes UA-RAO operators to summarize them, with empirical gains in localization on a 15-class power quality disturbance task using deep ensembles.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A Bayesian framework produces relevance attribution distributions for power quality disturbance classifiers so experts can select explanations by confidence percentiles.
citing papers explorer
-
A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification
Formalizes explanation distributions from BNNs via push-forward measures and proposes UA-RAO operators to summarize them, with empirical gains in localization on a 15-class power quality disturbance task using deep ensembles.
-
A Bayesian Framework for Uncertainty-Aware Explanations in Power Quality Disturbance Classification
A Bayesian framework produces relevance attribution distributions for power quality disturbance classifiers so experts can select explanations by confidence percentiles.