A push-forward formalism turns Bayesian model uncertainty into a distribution over attribution maps, and summary operators (mean, variance, quantiles) improve or reveal localization behavior in power-quality classification.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification
A push-forward formalism turns Bayesian model uncertainty into a distribution over attribution maps, and summary operators (mean, variance, quantiles) improve or reveal localization behavior in power-quality classification.