Explainable artificial intelligence: an analytical review

被引:398
作者
Angelov, Plamen P. [1 ,2 ]
Soares, Eduardo A. [1 ,2 ]
Jiang, Richard [1 ,2 ]
Arnold, Nicholas I. [1 ,3 ]
Atkinson, Peter M. [2 ,3 ]
机构
[1] Univ Lancaster, Sch Comp & Commun, Lancaster LA1 4WA, England
[2] Lancaster Intelligent Robot & Autonomous Syst LIR, Lancaster, England
[3] Univ Lancaster, Lancaster Environm Ctr, Lancaster, England
基金
英国工程与自然科学研究理事会;
关键词
black-box models; deep learning; explainable AI; machine learning; prototype-based models; surrogate models; BLACK-BOX; NEURAL-NETWORKS; EXPLANATIONS;
D O I
10.1002/widm.1424
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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
引用
收藏
页数:13
相关论文
共 73 条
[1]   Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].
Adadi, Amina ;
Berrada, Mohammed .
IEEE ACCESS, 2018, 6 :52138-52160
[2]  
Ancona M., 2018, Towards better understanding of gradient-based attribution methods for deep neural networks, DOI DOI 10.1109/TNSE.2020.2996738
[3]   Towards explainable deep neural networks (xDNN) [J].
Angelov, Plamen ;
Soares, Eduardo .
NEURAL NETWORKS, 2020, 130 :185-194
[4]   Toward Anthropomorphic Machine Learning [J].
Angelov, Plamen P. ;
Gu, Xiaowei .
COMPUTER, 2018, 51 (09) :18-27
[5]  
Nguyen A, 2015, PROC CVPR IEEE, P427, DOI 10.1109/CVPR.2015.7298640
[6]  
[Anonymous], 2001, Handbook of automated reasoning
[7]  
[Anonymous], 2017, What do we need to build explainable AI systems for the medical domain? (Ml)
[8]   On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation [J].
Bach, Sebastian ;
Binder, Alexander ;
Montavon, Gregoire ;
Klauschen, Frederick ;
Mueller, Klaus-Robert ;
Samek, Wojciech .
PLOS ONE, 2015, 10 (07)
[9]   Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI [J].
Barredo Arrieta, Alejandro ;
Diaz-Rodriguez, Natalia ;
Del Ser, Javier ;
Bennetot, Adrien ;
Tabik, Siham ;
Barbado, Alberto ;
Garcia, Salvador ;
Gil-Lopez, Sergio ;
Molina, Daniel ;
Benjamins, Richard ;
Chatila, Raja ;
Herrera, Francisco .
INFORMATION FUSION, 2020, 58 :82-115
[10]   PROTOTYPE SELECTION FOR INTERPRETABLE CLASSIFICATION [J].
Bien, Jacob ;
Tibshirani, Robert .
ANNALS OF APPLIED STATISTICS, 2011, 5 (04) :2403-2424