Cybertrust: From Explainable to Actionable and Interpretable Artificial Intelligence
Igor Linkov, Stephanie Galaitsi, Benjamin D. Trump, Jeffrey M. Keisler, Alexander Kott
Abstract
We argue that artificial intelligence (AI) systems should be designed with features that build trust by bringing decision-analytic perspectives into AI. Actionable and interpretable AI will incorporate explicit quantifications and visualizations of user confidence in AI recommendations.
Topics & Concepts
Computer scienceArtificial intelligenceApplications of artificial intelligenceData scienceMachine learningBlockchain Technology Applications and SecurityCybercrime and Law Enforcement StudiesSpam and Phishing Detection