Asking "Why' in AI: Explainability of intelligent systems-perspectives and challenges

被引：79

作者：

Preece, Alun ^{[1
]}

机构：

[1] Cardiff Univ, Crime & Secur Res Inst, Friary House,Greyfriars Rd, Cardiff CF10 3AE, S Glam, Wales

来源：

INTELLIGENT SYSTEMS IN ACCOUNTING FINANCE & MANAGEMENT | 2018年 / 25卷 / 02期

关键词：

artificial intelligence; explainability; interpretability; machine learning;

D O I：

10.1002/isaf.1422

中图分类号：

F8 [财政、金融];

学科分类号：

0202 ;

摘要：

Recent rapid progress in machine learning (ML), particularly so-called deep learning', has led to a resurgence in interest in explainability of artificial intelligence (AI) systems, reviving an area of research dating back to the 1970s. The aim of this article is to view current issues concerning ML-based AI systems from the perspective of classical AI, showing that the fundamental problems are far from new, and arguing that elements of that earlier work offer routes to making progress towards explainable AI today.

引用

页码：63 / 72

页数：10

共 50 条

[1] Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives
Langer, Markus
Baum, Kevin
Hartmann, Kathrin
Hessel, Stefan
Speith, Timo
Wahl, Jonas
[J]. 29TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE WORKSHOPS (REW 2021), 2021, : 164 - 168
[2] INTELLIGENT WEARABLE SYSTEMS ACHIEVEMENTS, CHALLENGES AND PERSPECTIVES
Lymberis, Andreas
[J]. BIOMEDICAL APPLICATIONS OF SMART MATERIALS, NANOTECHNOLOGY AND MICRO/NANO ENGINEERING, 2009, 57 : 88 - 93
[3] Responsibility and Explainability in Using Intelligent Systems
Wilbik, Anna
Grefen, Paul
[J]. INNOVATIONS FOR COMMUNITY SERVICES, I4CS 2024, 2024, 2109 : 3 - 14
[4] Developing and Experimenting on Approaches to Explainability in AI Systems
Zhang, Yuhao
McAreavey, Kevin
Liu, Weiru
[J]. ICAART: PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 2, 2022, : 518 - 527
[5] AI explainability and governance in smart energy systems: A review
Alsaigh, Roba
Mehmood, Rashid
Katib, Iyad
[J]. FRONTIERS IN ENERGY RESEARCH, 2023, 11
[6] Candidate Solutions for Defining Explainability Requirements of AI Systems
Balasubramaniam, Nagadivya
Kauppinen, Marjo
Truong, Hong-Linh
Kujala, Sari
[J]. REQUIREMENTS ENGINEERING: FOUNDATION FOR SOFTWARE QUALITY, REFSQ 2024, 2024, 14588 : 129 - 146
[7] Transparency and Explainability of AI Systems: Ethical Guidelines in Practice
Balasubramaniam, Nagadivya
Kauppinen, Marjo
Hiekkanen, Kari
Kujala, Sari
[J]. REQUIREMENTS ENGINEERING: FOUNDATION FOR SOFTWARE QUALITY, REFSQ 2022, 2022, 13216 : 3 - 18
[8] An objective metric for Explainable AI: How and why to estimate the degree of explainability
Sovrano, Francesco
Vitali, Fabio
[J]. KNOWLEDGE-BASED SYSTEMS, 2023, 278
[9] Creating meaningful work in the age of AI: explainable AI, explainability, and why it matters to organizational designers
Wulff, Kristin
Finnestrand, Hanne
[J]. AI & SOCIETY, 2024, 39 (04) : 1843 - 1856
[10] Expanding Explainability: Towards Social Transparency in AI systems
Ehsan, Upol
Liao, Q. Vera
Muller, Michael
Riedl, Mark O.
Weisz, Justin D.
[J]. CHI '21: PROCEEDINGS OF THE 2021 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, 2021,

← 1 2 3 4 5 →