arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.07074cs.AIcs.CYcs.HC
收藏

自动决策中人工决策的内容、原因和方式

The What, the Why, and the How of Artificial Explanations in Automated Decision-Making

City, University of London(伦敦大学城市学院)

Tarek R. Besold, Sara L. Uckelman

摘要:

越来越多的人工智能以自动化系统的形式融入决策过程,不仅突出了决策理论对自动化系统的重要性,而且还强调了这些决策过程对参与其中的人的解释的必要性。传统实在论对解释的解释是一种关系,这种关系在一个人和一个人之间永远保持(或不保持),不足以解释人为决策程序所需要的解释概念。我们提供了一个替代帐户的解释,用于自动决策的背景下,使解释的认知现象,是依赖于上下文。对解释的这种解释更好地说明了我们谈论和使用解释和衍生概念(如“解释力”)的方式,也使我们能够区分不需要具有认识方面的原因或原因与具有认识方面的解释。在此理论背景下,我们然后审查现有的方法来解释人工智能和机器学习,并建议desiderata真正可解释的决策系统应该履行。

英文摘要:

The increasing incorporation of Artificial Intelligence in the form of automated systems into decision-making procedures highlights not only the importance of decision theory for automated systems but also the need for these decision procedures to be explainable to the people involved in them. Traditional realist accounts of explanation, wherein explanation is a relation that holds (or does not hold) eternally between an explanans and an explanandum, are not adequate to account for the notion of explanation required for artificial decision procedures. We offer an alternative account of explanation as used in the context of automated decision-making that makes explanation an epistemic phenomenon, and one that is dependent on context. This account of explanation better accounts for the way that we talk about, and use, explanations and derived concepts, such as `explanatory power', and also allows us to differentiate between reasons or causes on the one hand, which do not need to have an epistemic aspect, and explanations on the other, which do have such an aspect. Against this theoretical backdrop we then review existing approaches to explanation in Artificial Intelligence and Machine Learning, and suggest desiderata which truly explainable decision systems should fulfill.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑