EVolutionary Independent DEtermiNistiC Explanation
Vincenzo Dentamaro, Paolo Giglio, Donato Impedovo, Giuseppe Pirlo

TL;DR
EVIDENCE is a new deterministic, model-independent explanation method for black-box AI models that improves interpretability and accuracy across diverse datasets, outperforming existing explainability techniques.
Contribution
The paper introduces EVIDENCE, a mathematically formalized, deterministic explanation approach that enhances signal extraction and model transparency in AI systems.
Findings
EVIDENCE improved COVID-19 diagnostic precision by 32%.
Achieved near-perfect F1-Score of 0.997 in Parkinson's classification.
Maintained high AUC of 0.996 in music genre classification.
Abstract
The widespread use of artificial intelligence deep neural networks in fields such as medicine and engineering necessitates understanding their decision-making processes. Current explainability methods often produce inconsistent results and struggle to highlight essential signals influencing model inferences. This paper introduces the Evolutionary Independent Deterministic Explanation (EVIDENCE) theory, a novel approach offering a deterministic, model-independent method for extracting significant signals from black-box models. EVIDENCE theory, grounded in robust mathematical formalization, is validated through empirical tests on diverse datasets, including COVID-19 audio diagnostics, Parkinson's disease voice recordings, and the George Tzanetakis music classification dataset (GTZAN). Practical applications of EVIDENCE include improving diagnostic accuracy in healthcare and enhancing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsModel Reduction and Neural Networks · Advanced Control Systems Optimization
MethodsShapley Additive Explanations · Local Interpretable Model-Agnostic Explanations
