From Features Engineering to Scenarios Engineering for Trustworthy AI: I&I, C&C, and V&V

doi:10.1109/MIS.2022.3197950

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	From Features Engineering to Scenarios Engineering for Trustworthy AI: I&I, C&C, and V&V
	Li, Xuan 1; Ye, Peijun2 ; Li, Juanjuan2 ; Liu, Zhongmin 3; Cao, Longbing 4; Wang, Fei-Yue5
发表期刊	IEEE INTELLIGENT SYSTEMS
ISSN	1541-1672
	2022-07-01
卷号	37 期号:4 页码:18-26
通讯作者	Li, Xuan(lix05@pcl.ac.cn)
摘要	Artificial intelligence (AI)'s rapid development has produced a variety of state-of-the-art models and methods that rely on network architectures and features engineering. However, some AI approaches achieve high accurate results only at the expense of interpretability and reliability. These problems may easily lead to bad experiences, lower trust levels, and systematic or even catastrophic risks. This article introduces the theoretical framework of scenarios engineering for building trustworthy AI techniques. We propose six key dimensions, including intelligence and index, calibration and certification, and verification and validation to achieve more robust and trusting AI, and address issues for future research directions and applications along this direction.
DOI	10.1109/MIS.2022.3197950
关键词[WOS]	INTELLIGENCE ; ECOLOGY ; MODEL
收录类别	SCI
语种	英语
资助项目	Science and Technology Development Fund, Macau SAR[0050/2020/A1] ; International Partnership Program of The Chinese Academy of Sciences[GJHZ202112] ; National Natural Science Foundation of China[62103411] ; Young Elite Scientists Sponsorship Program of China Association of Science and Technology[YESS20210289] ; China Postdoctoral Science Foundation[2020TQ1057] ; China Postdoctoral Science Foundation[2020M682823]
项目资助者	Science and Technology Development Fund, Macau SAR ; International Partnership Program of The Chinese Academy of Sciences ; National Natural Science Foundation of China ; Young Elite Scientists Sponsorship Program of China Association of Science and Technology ; China Postdoctoral Science Foundation
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000858007500003
出版者	IEEE COMPUTER SOC
引用统计	被引频次：72[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/50389
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Li, Xuan
作者单位	1.Peng Cheng Lab, Shenzhen 518000, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.North Automat Control Technol Inst, Taiyuan 030006, Peoples R China 4.Univ Technol Sydney, Sydney, NSW 2007, Australia 5.Chinese Acad Sci, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Xuan,Ye, Peijun,Li, Juanjuan,et al. From Features Engineering to Scenarios Engineering for Trustworthy AI: I&I, C&C, and V&V[J]. IEEE INTELLIGENT SYSTEMS,2022,37(4):18-26.
APA	Li, Xuan,Ye, Peijun,Li, Juanjuan,Liu, Zhongmin,Cao, Longbing,&Wang, Fei-Yue.(2022).From Features Engineering to Scenarios Engineering for Trustworthy AI: I&I, C&C, and V&V.IEEE INTELLIGENT SYSTEMS,37(4),18-26.
MLA	Li, Xuan,et al."From Features Engineering to Scenarios Engineering for Trustworthy AI: I&I, C&C, and V&V".IEEE INTELLIGENT SYSTEMS 37.4(2022):18-26.