Evaluating Architectural Safeguards for Uncertain AI Black-Box Components

• Huvudskapare: Scheerer, Max (auth)
• Materialtyp: Elektronisk Bokavsnitt
• Språk: engelska
• Publicerad: KIT Scientific Publishing 2023
• Serie: The Karlsruhe Series on Software Design and Quality
• Ämnen: Mathematics & science; self-adaptive systems; safeguarding AI; architectural reliability analysis; Software engineering; Selbst-Adaptive Systeme; Absicherung von KI; architekturelle Zuverlässigkeitsanalyse; Softwaretechnik
• Länkar: DOAB: download the publication; DOAB: description of the publication

Although tremendous progress has been made in Artificial Intelligence (AI), it entails new challenges. The growing complexity of learning tasks requires more complex AI components, which increasingly exhibit unreliable behaviour. In this book, we present a model-driven approach to model architectura...