Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

分类学(生物学) 人工智能 计算机科学 领域(数学) 软件部署 问责 数据科学 管理科学 知识管理 政治学 工程类 软件工程 生物 植物 数学 纯数学 法学
作者
Alejandro Barredo Arrieta,Natalia Díaz-Rodríguez,Javier Del Ser,Adrien Bennetot,Siham Tabik,Alberto Barbado,Salvador García,Sergio Gil-López,Daniel Molina,Richard Benjamins,Raja Chatila,Francisco Herrera
出处
期刊:Cornell University - arXiv 被引量:14
标识
DOI:10.48550/arxiv.1910.10045
摘要

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
耶耶耶完成签到 ,获得积分10
6秒前
logolush完成签到 ,获得积分10
7秒前
cqnuly发布了新的文献求助30
8秒前
顾矜应助李谢谢采纳,获得10
8秒前
15秒前
韧迹完成签到 ,获得积分10
16秒前
溪夕er完成签到,获得积分10
18秒前
20秒前
21秒前
李谢谢发布了新的文献求助10
27秒前
从容保温杯完成签到,获得积分10
28秒前
柒八染完成签到 ,获得积分10
31秒前
燕山堂完成签到 ,获得积分10
33秒前
坚定的映寒完成签到 ,获得积分10
37秒前
TheaGao完成签到 ,获得积分10
53秒前
yinhe完成签到 ,获得积分10
1分钟前
wu123关注了科研通微信公众号
1分钟前
cqnuly完成签到,获得积分10
1分钟前
温如军完成签到 ,获得积分10
1分钟前
MS903完成签到 ,获得积分10
1分钟前
1分钟前
1分钟前
中恐完成签到,获得积分10
1分钟前
CJW完成签到 ,获得积分10
1分钟前
wu123发布了新的文献求助10
1分钟前
楚襄谷完成签到 ,获得积分10
1分钟前
成就幻波发布了新的文献求助10
1分钟前
胜天半子完成签到 ,获得积分10
1分钟前
噼里啪啦完成签到,获得积分10
1分钟前
WSY完成签到 ,获得积分10
1分钟前
旺仔完成签到 ,获得积分10
2分钟前
2分钟前
song完成签到 ,获得积分10
2分钟前
bai发布了新的文献求助10
2分钟前
俭朴的乐巧完成签到 ,获得积分10
2分钟前
monster完成签到 ,获得积分10
2分钟前
懵懂的紫萍完成签到 ,获得积分10
2分钟前
bai完成签到,获得积分10
2分钟前
浮云完成签到,获得积分10
2分钟前
妮子拉完成签到,获得积分10
2分钟前
高分求助中
Becoming: An Introduction to Jung's Concept of Individuation 600
Ore genesis in the Zambian Copperbelt with particular reference to the northern sector of the Chambishi basin 500
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
A new species of Velataspis (Hemiptera Coccoidea Diaspididae) from tea in Assam 500
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 500
Sarcolestes leedsi Lydekker, an ankylosaurian dinosaur from the Middle Jurassic of England 450
Die Gottesanbeterin: Mantis religiosa: 656 400
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3164826
求助须知:如何正确求助?哪些是违规求助? 2815925
关于积分的说明 7910558
捐赠科研通 2475504
什么是DOI,文献DOI怎么找? 1318250
科研通“疑难数据库(出版商)”最低求助积分说明 632035
版权声明 602296