透明度(行为)
计算机科学
碎片(计算)
数据科学
背景(考古学)
人工智能
计算机安全
古生物学
生物
操作系统
作者
Kashyap Haresamudram,Stefan Larsson,Fredrik Heintz
出处
期刊:IEEE Computer
[Institute of Electrical and Electronics Engineers]
日期:2023-02-01
卷期号:56 (2): 93-100
被引量:10
标识
DOI:10.1109/mc.2022.3213181
摘要
The concept of transparency is fragmented in artificial intelligence (AI) research, often limited to transparency of the algorithm alone. We propose that AI transparency operates on three levels—algorithmic, interaction, and social—all of which need to be considered to build trust in AI. We expand upon these levels using current research directions, and identify research gaps resulting from the conceptual fragmentation of AI transparency highlighted within the context of the three levels.
科研通智能强力驱动
Strongly Powered by AbleSci AI