Foundations of Symbolic Languages for Model Interpretability Marcelo Arenas 1,4, Daniel Baez

Neural Information Processing Systems 

Several queries and scores have been proposed to explain individual predictions made by ML models. Examples include queries based on "anchors", which are parts of an instance that are sufficient to justify its classification, and "feature-perturbation" scores such as SHAP .

Similar Docs  Excel Report  more

TitleSimilaritySource
None found