◉ 简单语言

Explainable AI bedeutet: Methoden und Techniken um KI-Entscheidungen für Menschen verstaendlich zu machen. Das ist wichtig, weil KI-Systeme heute überall eingesetzt werden und Regeln brauchen, damit sie sicher und fair funktionieren.

◈ 专家级别

Methoden und Techniken um KI-Entscheidungen für Menschen verstaendlich zu machen. [NIST AI RMF] efforts on the implementing entity, including the level of necessary resources and the need to safeguard proprietary information. Maintaining the provenance of training data and supporting attribution of the AI system’s decisions to subsets of training data can assist with both transparency and acco [NIST AI RMF] NIST AI 100-1 Artificial Intelligence Risk Management Framework (AI RMF 1.0) NIST AI 100-1 Artificial Intelligence Risk Management Framework (AI RMF 1.0) This publication is available free of charge from: https://doi.org/10.6028/NIST.AI.100-1 January 2023 U.S. Department of Commerce Gina M. Raimondo [NIST AI RMF] organizational practices are carried out in accord with “professional responsibility,” defined by ISO as an approach that “aims to ensure that professionals who design, develop, or deploy AI systems and applications or AI-based products or systems, recognize their unique position to exert influence

Methoden und Techniken um KI-Entscheidungen für Menschen verstaendlich zu machen.

Im Kontext von AI Governance ist Explainable AI eng verknüpft mit: Explainability, Interpretability, Transparency, Trustworthy Ai. Diese Konzepte bilden zusammen das Fundament einer verantwortungsvollen KI-Entwicklung und -Nutzung.

引用

"可解释AI(XAI)." Open Cognition Commons Foundation. https://opencognitioncommons.org/zh/glossary/explainable-ai. CC-BY 4.0.

机器可读元数据

{
  "@context": "https://schema.org",
  "@type": "DefinedTerm",
  "name": "可解释AI(XAI)",
  "description": "Methoden und Techniken um KI-Entscheidungen für Menschen verstaendlich zu machen.\n",
  "url": "https://opencognitioncommons.org/zh/glossary/explainable-ai",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "alternateName": [
    "XAI",
    "Explainable AI",
    "Erklärbare KI"
  ]
}