The coming of age of interpretable and explainable machine learning models

被引：58

作者：

Lisboa, P. J. G. ^{[1
]}

Saralajew, S. ^{[2
]}

Vellido, A. ^{[3
,4
]}

Fernandez-Domenech, R. ^{[3
,4
]}

Villmann, T. ^{[5
]}

机构：

[1] Liverpool John Moores Univ, Liverpool, England

[2] NEC Labs Europe GmbH, Heidelberg, Germany

[3] UPC BarcelonaTech, Dept Comp Sci, Barcelona, Spain

[4] UPC Res Ctr, IDEAI, Barcelona, Spain

[5] Univ Appl Sci Mittweida, Saxon Inst Comp Intelligence & Machine Learning, Mittweida, Germany

来源：

NEUROCOMPUTING | 2023年 / 535卷

关键词：

XAI; Interpretable ML; Explainable ML; Transparent AI; AUTOMATED DECISION-MAKING; NEURAL-NETWORKS; ARTIFICIAL-INTELLIGENCE; CLASSIFICATION; EXPLANATION;

D O I：

10.1016/j.neucom.2023.02.040

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Machine-learning-based systems are now part of a wide array of real-world applications seamlessly embedded in the social realm. In the wake of this realization, strict legal regulations for these systems are currently being developed, addressing some of the risks they may pose. This is the coming of age of the concepts of interpretability and explainability in machine-learning-based data analysis, which can no longer be seen just as an academic research problem. In this paper, we discuss explainable and interpretable machine learning as post hoc and ante-hoc strategies to address regulatory restrictions and highlight several aspects related to them, including their evaluation and assessment and the legal boundaries of application.(c) 2023 Elsevier B.V. All rights reserved.

引用

页码：25 / 39

页数：15

共 127 条

[1]

AAMODT A, 1994, AI COMMUN, V7, P39

[2]

Adebayo J., ADV NEURAL INFORM PR

[3]

Agarwal R., 2021, Advances in Neural Information Processing Systems, P1

[4] Organizational Transparency: Conceptualizations, Conditions, and Consequences [J].