About 50 results
Open links in new tab
  1. What is Explainable AI (XAI)? | IBM

    Nov 28, 2019 · AI explainability also helps an organization adopt a responsible approach to AI development. As AI becomes more advanced, humans are challenged to comprehend and retrace …

  2. Explainability - IBM

    Explainability example Per GDPR (General Data Protection Regulation), a guest must explicitly opt in to use the hotel room assistant. Additionally, they will be provided with a transparent UI to show how …

  3. 説明可能なAI(XAI)とは - IBM

    説明可能なAI(XAI)とは、機械学習アルゴリズムによって生成された結果や判断の根拠を、人間が理解し、信頼できるようにするための一連のプロセスや方法のことです。

  4. Cos'è l'AI spiegabile (XAI)? | IBM

    La cosiddetta AI spiegabile (o eXplainable AI , XAI) consente agli utenti umani di comprendere e ritenere affidabili i risultati e gli output generati mediante algoritmi di machine learning.

  5. How IBM makes AI based on trust, fairness and explainability

    For IBM, trust is a foundational pillar of AI. Check out our full Innovation panel to learn more about trust, fairness and governance with AI.

  6. What Is AI Interpretability? | IBM

    AI interpretability is the ability to understand and explain the decision-making processes that power artificial intelligence models.

  7. Configuring explainability - IBM

    In the Explainability section of your model configuration page, configure explainability to analyze the factors that influence your model outcomes. You can choose to configure local explanations to …

  8. 설명 가능한 AI(XAI)란 무엇인가요? | IBM

    설명 가능한 AI는 AI 모델과 이에 대한 예상되는 영향 및 잠재적 편향을 설명하는 데 사용됩니다. 이는 AI로 이루어지는 의사 결정에서 모델 정확성, 공정성, 투명성 및 결과를 특성화하는 데 도움이 됩니다. 설명 …

  9. What Is AI Transparency? | IBM

    Oct 30, 2023 · AI explainability, or explainable AI (XAI), is a set of processes and methods that allow human users to comprehend and trust the results and output created by machine learning models. …

  10. O que é IA explicável (XAI)? | IBM

    A Inteligência Artificial Explicável (XAI) permite que os usuários humanos compreendam e confiem nos resultados e saídas criados pelos algoritmos de aprendizado de máquina.