Explainable artificial intelligence: an analytical review

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...

Full description

Saved in:
Bibliographic Details
Published inWiley interdisciplinary reviews. Data mining and knowledge discovery Vol. 11; no. 5
Main Authors Angelov, Plamen P., Soares, Eduardo A., Jiang, Richard, Arnold, Nicholas I., Atkinson, Peter M.
Format Journal Article
LanguageEnglish
Published Hoboken, USA Wiley Periodicals, Inc 01.09.2021
Subjects
black‐box models
deep learning
explainable AI
machine learning
prototype‐based models
surrogate models
Online AccessGet full text

Cover

More Information
Summary: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. This article is categorized under: Technologies > Artificial Intelligence Fundamental Concepts of Data and Knowledge > Explainable AI Accuracy versus interpretability for different machine learning models.
Bibliography:Sushmita Mitra, Associate Editor and Witold Pedrycz, Editor‐in‐Chief
Edited by
ISSN:1942-4787
1942-4795
DOI:10.1002/widm.1424