Explaining the black box: When law controls AI
2020•researchportal.unamur.be
… This conception illustrates the different meanings of explainability which may relate to the
process, the capabilities or the decision and shows that, for some black box algorithms,
auditability of the algorithm may serve as an alternative to explanation to users. …
Whenever an AI system has a significant impact on people’s lives, it should be possible to
demand a suitable explanation of the AI system’s decision-making process. Such
explanation should be timely and adapted to the expertise of the stakeholder concerned (eg …
process, the capabilities or the decision and shows that, for some black box algorithms,
auditability of the algorithm may serve as an alternative to explanation to users. …
Whenever an AI system has a significant impact on people’s lives, it should be possible to
demand a suitable explanation of the AI system’s decision-making process. Such
explanation should be timely and adapted to the expertise of the stakeholder concerned (eg …
Abstract
The explainability of Artificial Intelligence algorithms, in particular Machine-Learning algorithms, has become a major concern for society. Policy-makers across the globe are starting to reply to such concern.
researchportal.unamur.be
以上显示的是最相近的搜索结果。 查看全部搜索结果