XAI-Explainable artificial intelligence

被引:958
|
作者
Gunning, David [1 ,7 ]
Stefik, Mark [2 ]
Choi, Jaesik [3 ]
Miller, Timothy [4 ]
Stumpf, Simone [5 ]
Yang, Guang-Zhong [6 ]
机构
[1] DARPA, 675 North Randolph St, Arlington, VA 22201 USA
[2] Palo Alto Res Ctr, 3333 Coyote Hill Rd, Palo Alto, CA 94304 USA
[3] Korea Adv Inst Sci & Technol, Grad Sch Artificial Intelligence, 291 Daehak Ro, Daejeon 34141, South Korea
[4] Univ Melbourne, Sch Comp & Informat Syst, Melbourne, Vic 3010, Australia
[5] City Univ London, Sch Math Comp Sci & Engn, Ctr HCI Design, London EC1V 0HB, England
[6] Shanghai Jiao Tong Univ, Inst Med Robot, Shanghai, Peoples R China
[7] Facebook AI Res, 770 Broadway, New York, NY 10003 USA
关键词
D O I
10.1126/scirobotics.aay7120
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Recent successes in machine learning (ML) have led to a new wave of artificial intelligence (AI) applications that offer extensive benefits to a diverse range of fields. However, many of these systems are not able to explain their autonomous decisions and actions to human users. Explanations may not be essential for certain AI applications, and some AI researchers argue that the emphasis on explanation is misplaced, too difficult to achieve, and perhaps unnecessary. However, for many critical applications in defense, medicine, finance, and law, explanations are essential for users to understand, trust, and effectively manage these new, artificially intelligent partners [see recent reviews (1-3)]. Copyright © 2019 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works
引用
收藏
页数:2
相关论文
共 50 条
  • [41] Introduction to the special section on eXplainable Artificial Intelligence (XAI): Methods, Applications, and Challenges (VSI-xai)
    Singh, Ashutosh Kumar
    Kumar, Jitendra
    Saxena, Deepika
    V. Vasilakos, Athanasios
    COMPUTERS & ELECTRICAL ENGINEERING, 2024, 120
  • [42] Explainable Artificial Intelligence (XAI) Supporting Public Administration Processes - On the Potential of XAI in Tax Audit Processes
    Mehdiyev, Nijat
    Houy, Constantin
    Gutermuth, Oliver
    Mayer, Lea
    Fettke, Peter
    INNOVATION THROUGH INFORMATION SYSTEMS, VOL I: A COLLECTION OF LATEST RESEARCH ON DOMAIN ISSUES, 2021, 46 : 413 - 428
  • [43] Revisiting the Performance-Explainability Trade -Off in Explainable Artificial Intelligence (XAI)
    Crook, Barnahy
    Schueter, Maximilian
    Speith, Timo
    2023 IEEE 31ST INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE WORKSHOPS, REW, 2023, : 316 - 324
  • [44] Explainable Artificial Intelligence (XAI) Surrogate Models for Chemical Process Design and Analysis
    Ko, Yuna
    Na, Jonggeol
    KOREAN CHEMICAL ENGINEERING RESEARCH, 2023, 61 (04): : 542 - 549
  • [45] Improving deep learning performance by using Explainable Artificial Intelligence (XAI) approaches
    Bento V.
    Kohler M.
    Diaz P.
    Mendoza L.
    Pacheco M.A.
    Discover Artificial Intelligence, 2021, 1 (01):
  • [46] An Explainable Artificial Intelligence (xAI) Framework for Improving Trust in Automated ATM Tools
    Hernandez, Carolina Sanchez
    Ayo, Samuel
    Panagiotakopoulos, Dimitrios
    2021 IEEE/AIAA 40TH DIGITAL AVIONICS SYSTEMS CONFERENCE (DASC), 2021,
  • [47] A methodological and theoretical framework for implementing explainable artificial intelligence (XAI) in business applications
    Tchuente, Dieudonne
    Lonlac, Jerry
    Kamsu-Foguem, Bernard
    COMPUTERS IN INDUSTRY, 2024, 155
  • [48] CL-XAI: Toward Enriched Cognitive Learning with Explainable Artificial Intelligence
    Suffian, Muhammad
    Kuhl, Ulrike
    Alonso-Moral, Jose Maria
    Bogliolo, Alessandro
    SOFTWARE ENGINEERING AND FORMAL METHODS, SEFM 2023 COLLOCATED WORKSHOPS, CIFMA 2023 AND OPENCERT 2023, 2024, 14568 : 5 - 27
  • [49] Explainable Artificial Intelligence (XAI) for Oncological Ultrasound Image Analysis: A Systematic Review
    Wyatt, Lucie S.
    van Karnenbeek, Lennard M.
    Wijkhuizen, Mark
    Geldof, Freija
    Dashtbozorg, Behdad
    APPLIED SCIENCES-BASEL, 2024, 14 (18):
  • [50] Explainable Artificial Intelligence (XAI): A Systematic Literature Review on Taxonomies and Applications in Finance
    Martins, Tiago
    de Almeida, Ana Maria
    Cardoso, Elsa
    Nunes, Luis
    IEEE ACCESS, 2024, 12 : 618 - 629