arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.12604cs.AI
收藏

可信AI:决定去决定什么

Trustworthy AI: Deciding What to Decide

University of Luxembourg(卢森堡大学);Monash University(莫纳什大学);Dongbei University of Finance and Economics(东北财经大学)

Caesar Wu, Yuan-Fang Li, Jian Li, Jingjing Xu, Bouvry Pascal

AI总结:

针对AI决策中信息可信度与黑盒问题,提出包含表示空间、损失函数和优化器及十二个属性的Trustworthy AI (TAI)框架,并构建最优预测模型应用于科技领域信用违约掉期战略投资决策。

摘要:

在参与战略决策时,我们经常面临海量信息与数据。当某些证据相互矛盾或变得悖论时,情况会进一步复杂化。当我们采用人工智能(AI)系统进行决策时,主要挑战在于如何确定哪些信息可以被信任。这个问题被称为决定去决定什么或可信AI。然而,AI系统本身常被视为不透明的黑盒。我们提出一种新方法来解决此问题,引入一个名为Trustworthy AI (TAI)的新颖框架,涵盖AI的三个关键组件:表示空间、损失函数和优化器。每个组件与四个TAI属性松散耦合。该框架共包含十二个TAI属性。我们旨在通过定量和定性研究方法开展TAI实验,以满足决策情境下的TAI属性。该框架使我们能够构建一个由给定数据集训练的最优预测模型,应用于科技领域的信用违约掉期(CDS)战略投资决策。最后,我们提出了对TAI研究未来方向的看法。

英文摘要:

When engaging in strategic decision-making, we are frequently confronted with overwhelming information and data. The situation can be further complicated when certain pieces of evidence contradict each other or become paradoxical. The primary challenge is how to determine which information can be trusted when we adopt Artificial Intelligence (AI) systems for decision-making. This issue is known as deciding what to decide or Trustworthy AI. However, the AI system itself is often considered an opaque black box. We propose a new approach to address this issue by introducing a novel framework of Trustworthy AI (TAI) encompassing three crucial components of AI: representation space, loss function, and optimizer. Each component is loosely coupled with four TAI properties. Altogether, the framework consists of twelve TAI properties. We aim to use this framework to conduct the TAI experiments by quantitive and qualitative research methods to satisfy TAI properties for the decision-making context. The framework allows us to formulate an optimal prediction model trained by the given dataset for applying the strategic investment decision of credit default swaps (CDS) in the technology sector. Finally, we provide our view of the future direction of TAI research

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。

↑