Home > Research > Publications & Outputs > Explainable artificial intelligence

Electronic data

  • WIDM_1424_updated (1)

    Accepted author manuscript, 1.93 MB, PDF document

    Available under license: CC BY-NC-ND

Links

Text available via DOI:

View graph of relations

Explainable artificial intelligence: an analytical review

Research output: Contribution to journalJournal articlepeer-review

E-pub ahead of print

Standard

Explainable artificial intelligence : an analytical review. / Angelov, Plamen; Almeida Soares, Eduardo; Jiang, Richard; Arnold, Nicholas; Atkinson, Peter.

In: WIREs Data Mining and Knowledge Discovery, 12.07.2021.

Research output: Contribution to journalJournal articlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{89f33fca4d8b4b6a8124613c9bdab22f,
title = "Explainable artificial intelligence: an analytical review",
abstract = "This paper provides a brief analytical review of the current state-of-the-art in relation to the explainability of artificial intelligence in the context of recent advances in machine learning and deep learning. The paper starts with a brief historical introduction and a taxonomy, and formulates the main challenges in terms of explainability building on the recently formulated National Institute of Standards four principles of explainability. Recently published methods related to the topic are then critically reviewed and analyzed. Finally, future directions for research are suggested.",
keywords = "black-box models, deep learning, explainable AI, machine learning, prototype-based models, surrogate models",
author = "Plamen Angelov and {Almeida Soares}, Eduardo and Richard Jiang and Nicholas Arnold and Peter Atkinson",
year = "2021",
month = jul,
day = "12",
doi = "10.1002/widm.1424",
language = "English",
journal = "WIREs Data Mining and Knowledge Discovery",
issn = "1942-4795",
publisher = "Wiley",

}

RIS

TY - JOUR

T1 - Explainable artificial intelligence

T2 - an analytical review

AU - Angelov, Plamen

AU - Almeida Soares, Eduardo

AU - Jiang, Richard

AU - Arnold, Nicholas

AU - Atkinson, Peter

PY - 2021/7/12

Y1 - 2021/7/12

N2 - This paper provides a brief analytical review of the current state-of-the-art in relation to the explainability of artificial intelligence in the context of recent advances in machine learning and deep learning. The paper starts with a brief historical introduction and a taxonomy, and formulates the main challenges in terms of explainability building on the recently formulated National Institute of Standards four principles of explainability. Recently published methods related to the topic are then critically reviewed and analyzed. Finally, future directions for research are suggested.

AB - This paper provides a brief analytical review of the current state-of-the-art in relation to the explainability of artificial intelligence in the context of recent advances in machine learning and deep learning. The paper starts with a brief historical introduction and a taxonomy, and formulates the main challenges in terms of explainability building on the recently formulated National Institute of Standards four principles of explainability. Recently published methods related to the topic are then critically reviewed and analyzed. Finally, future directions for research are suggested.

KW - black-box models

KW - deep learning

KW - explainable AI

KW - machine learning

KW - prototype-based models

KW - surrogate models

U2 - 10.1002/widm.1424

DO - 10.1002/widm.1424

M3 - Journal article

JO - WIREs Data Mining and Knowledge Discovery

JF - WIREs Data Mining and Knowledge Discovery

SN - 1942-4795

ER -