A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification
Researchers have introduced a new framework for explainable AI (XAI) that incorporates uncertainty awareness, moving beyond deterministic attribution maps. This approach formalizes the 'explanation distribution' derived from Bayesian neural networks and proposes operators to summarize this distribution using measures like mean and variance. The framework was tested on a power quality disturbance classification task, showing that deep ensembles with the mean operator improved localization accuracy compared to deterministic methods and revealed uncertainty patterns not present in standard attributions. AI
IMPACT Introduces a novel method for understanding AI model behavior by quantifying uncertainty in explanations, potentially improving decision-making in critical applications.