TY - RPRT A1 - Olschewski, Detlef A1 - Bluhm, André A1 - Firnkorn, Joerg A1 - Lucieri, Adriano A1 - Palacio, Sebastian A1 - Streppel, Yeji A1 - Zednik, Carlos A1 - Görge, Rebekka A1 - Poretschkin, Maximilian A1 - Becker, Nikolas A1 - Zielke, Thomas A1 - Kruschel, Christian A1 - Neumann-Brosig, Matthias A1 - Bäuerle, Stephen A1 - Eifert, Marton A1 - López, Erik Martori A1 - Assion, Felix A1 - Seyerlein-Klug, Annegrit A1 - Schmid, Ute A1 - Haufe, Stefan A1 - Gautier, Antoine A1 - Bieringer, Lukas A1 - Besold, Tarek R. A1 - Cremers, Armin B. T1 - DIN SPEC 92001-3 Artificial Intelligence - Life Cycle Processes and Quality Requirements - Part 3: Explainability N2 - DIN SPEC 92001-3 Artificial Intelligence – Life Cycle Processes and Quality Requirements. Artificial Intelligence has become a game-changer, but its impact must be approached responsibly. This is the third document in a series, and it aims to ensure that AI systems are developed, deployed, and used efficiently, responsibly, and in a trustworthy way. It focuses on “Explainability” – the ability to understand how AI makes decisions. This DIN SPEC 92001-3 provides a domain-independent guide on promoting explainability throughout the AI system’s life cycle. It tackles “opacity”, describing sources and effects of opacity in AI and how explanations can mitigate them. The goal is to foster a better understanding and effective use of Explainable AI across various applications, fostering principles of trust and transparency in AI-based systems. This DIN SPEC is the result of „Zertifizierung von Standard-KI-Anwendungen (Zertifizierte KI project)“ https://www.zertifizierte-ki.de/. The publication is available for free at Beuth Verlag GmbH www.beuth.de - plus the search for "DIN SPEC 92001-3" Y1 - 2023 PB - Beuth Verlag ER -