Explainable artificial intelligence: an analytical review. (12th July 2021)

• Record Type: Journal Article
• Authors: Angelov, Plamen P.; Soares, Eduardo A.; Jiang, Richard; Arnold, Nicholas I.; Atkinson, Peter M.
• Is Part Of: Wiley interdisciplinary reviews. Volume 11:Number 5(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-07-12
• Subjects: black‐box models -- deep learning -- explainable AI -- machine learning -- prototype‐based models -- surrogate models; Data mining -- Periodicals; 006.31205
• DOI: 10.1002/widm.1424
• Languages: English
• ISSNs: 1942-4787

Abstract

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. This article is categorized under: Technologies > Artificial Intelligence Fundamental Concepts of Data and Knowledge > Explainable AI Abstract : Accuracy versus interpretability for different machine learning models.