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 2112.00591cs.AIcs.CYcs.GTcs.NAmath.NA
收藏

使用因果推理的AI保证:公共政策的应用

AI Assurance using Causal Inference: Application to Public Policy

Commonwealth Cyber Initiative, Virginia Tech(弗吉尼亚理工大学联邦网络倡议)

Andrei Svetovidov, Abdul Rahman, Feras A. Batarseh

摘要:

开发和实施基于人工智能的解决方案可以帮助州和联邦政府机构、研究机构和商业公司增强决策过程,实现连锁经营自动化,并减少自然和人力资源的消耗。与此同时,实践中使用的大多数人工智能方法只能表示为“黑匣子”,缺乏透明度。这最终可能导致意想不到的结果,并破坏对此类系统的信任。因此,不仅要开发有效和强大的人工智能系统,而且要确保其内部流程是可解释和公平的。本章的目标是以美国经济的技术部门为例,介绍为具有高影响力决策的人工智能系统设计保证方法的主题。我们解释了这些领域将如何受益于揭示数据集中的关键指标之间的因果关系,通过提供技术经济数据集的因果实验。回顾了几种因果推理方法和AI保证技术,并演示了将数据转换为图形结构数据集的过程。

英文摘要:

Developing and implementing AI-based solutions help state and federal government agencies, research institutions, and commercial companies enhance decision-making processes, automate chain operations, and reduce the consumption of natural and human resources. At the same time, most AI approaches used in practice can only be represented as "black boxes" and suffer from the lack of transparency. This can eventually lead to unexpected outcomes and undermine trust in such systems. Therefore, it is crucial not only to develop effective and robust AI systems, but to make sure their internal processes are explainable and fair. Our goal in this chapter is to introduce the topic of designing assurance methods for AI systems with high-impact decisions using the example of the technology sector of the US economy. We explain how these fields would benefit from revealing cause-effect relationships between key metrics in the dataset by providing the causal experiment on technology economics dataset. Several causal inference approaches and AI assurance techniques are reviewed and the transformation of the data into a graph-structured dataset is demonstrated.

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。

↑