Explainability Is <i>Not</i> a Game
João Marques‐Silva, Xuanxiang Huang
Abstract
When the decisions of ML models impact people, one should expect explanations to offer the strongest guarantees of rigor. However, the most popular XAI approaches offer none.
Topics & Concepts
Computer scienceExplainable Artificial Intelligence (XAI)Scientific Computing and Data ManagementMachine Learning in Healthcare