Explainable Artificial Intelligence: Importance, Use Domains, Stages, Output Shapes, and Challenges

被引:1
作者
Ullah, Naeem [1 ]
Khan, Javed Ali [2 ]
De Falco, Ivanoe [3 ]
Sannino, Giovanna [3 ]
机构
[1] Univ Naples Federico II, Dept Elect Engn & Informat Technol, Naples, Italy
[2] Univ Hertfordshire, Dept Comp Sci, Hatfield, England
[3] Natl Res Council CNR, Inst High Performance Comp & Networking ICAR, Naples, Italy
关键词
DEEP NEURAL-NETWORKS; XAI; AI; CLASSIFICATION; TRUSTWORTHY;
D O I
10.1145/3705724
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
There is an urgent need in many application areas for eXplainable ArtificiaI Intelligence (XAI) approaches to boost people's confidence and trust in Artificial Intelligence methods. Current works concentrate on specific aspects of XAI and avoid a comprehensive perspective. This study undertakes a systematic survey of importance, approaches, methods, and application domains to address this gap and provide a comprehensive understanding of the XAI domain. Applying the Systematic Literature Review approach has resulted in finding and discussing 155 papers, allowing a wide discussion on the strengths, limitations, and challenges of XAI methods and future research directions.
引用
收藏
页数:36
相关论文
共 168 条
  • [1] An XAI-based adversarial training approach for cyber-threat detection
    Al-Essa, Malik
    Andresini, Giuseppina
    Appice, Annalisa
    Malerba, Donato
    [J]. 2022 IEEE INTL CONF ON DEPENDABLE, AUTONOMIC AND SECURE COMPUTING, INTL CONF ON PERVASIVE INTELLIGENCE AND COMPUTING, INTL CONF ON CLOUD AND BIG DATA COMPUTING, INTL CONF ON CYBER SCIENCE AND TECHNOLOGY CONGRESS (DASC/PICOM/CBDCOM/CYBERSCITECH), 2022, : 806 - 813
  • [2] Uncertain-CAM: Uncertainty-Based Ensemble Machine Voting for Improved COVID-19 CXR Classification and Explainability
    Aldhahi, Waleed
    Sull, Sanghoon
    [J]. DIAGNOSTICS, 2023, 13 (03)
  • [3] Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence
    Ali, Sajid
    Abuhmed, Tamer
    El-Sappagh, Shaker
    Muhammad, Khan
    Alonso-Moral, Jose M.
    Confalonieri, Roberto
    Guidotti, Riccardo
    Del Ser, Javier
    Diaz-Rodriguez, Natalia
    Herrera, Francisco
    [J]. INFORMATION FUSION, 2023, 99
  • [4] Amit Guy, 2022, INT WORKSH PROC MAN
  • [6] Energy Management in RFID-Sensor Networks: Taxonomy and Challenges
    Anjum, Shaik Shabana
    Noor, Rafidah Md
    Anisi, Mohammad Hossein
    Bin Ahmedy, Ismail
    Othman, Fazidah
    Alam, Muhammad
    Khan, Muhammad Khurram
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2019, 6 (01): : 250 - 266
  • [7] Assaf R, 2019, PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P6488
  • [8] A systematic survey on explainable AI applied to fake news detection
    Athira, A. B.
    Kumar, S. D. Madhu
    Chacko, Anu Mary
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 122
  • [9] ATLAS Collaboration, 2017, HEPData
  • [10] Enabling federated learning of explainable AI models within beyond-5G/6G networks
    Barcena, Jose Luis Corcuera
    Ducange, Pietro
    Marcelloni, Francesco
    Nardini, Giovanni
    Noferi, Alessandro
    Renda, Alessandro
    Ruffini, Fabrizio
    Schiavo, Alessio
    Stea, Giovanni
    Virdis, Antonio
    [J]. COMPUTER COMMUNICATIONS, 2023, 210 : 356 - 375