Toward verified artificial intelligence
Sanjit A. Seshia, Dorsa Sadigh, Shankar Sastry
Abstract
Making AI more trustworthy with a formal methods-based approach to AI system verification and validation.
Topics & Concepts
Computer scienceTrustworthinessArtificial intelligenceSoftware engineeringComputer securityAdversarial Robustness in Machine LearningFormal Methods in VerificationExplainable Artificial Intelligence (XAI)