Toward Human-Understandable, Explainable AI

被引：229

作者：

Hagras, Hani ^{[1
,2
,3
]}

机构：

[1] Univ Essex, Sch Comp Sci & Elect Engn, Colchester, Essex, England

[2] Univ Essex, Sch Comp Sci & Elect Engn, Res, Colchester, Essex, England

[3] Univ Essex, Sch Comp Sci & Elect Engn, Computat Intelligence Ctr, Colchester, Essex, England

来源：

COMPUTER | 2018年 / 51卷 / 09期

关键词：

CLASSIFICATION;

D O I：

10.1109/MC.2018.3620965

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Recent increases in computing power, coupled with rapid growth in the availability and quantity of data have rekindled our interest in the theory and applications of artificial intelligence (AI). However, for AI to be confidently rolled out by industries and governments, users want greater transparency through explainable AI (XAI) systems. The author introduces XAI concepts, and gives an overview of areas in need of further exploration-such as type-2 fuzzy logic systems-to ensure such systems can be fully understood and analyzed by the lay user.

引用

页码：28 / 36

页数：9

共 19 条

[1]

[Anonymous], 2017, AI UK READ WILL ABL

[2]

[Anonymous], 2017, ART INT MACH LEARN F

[3]

[Anonymous], 2016, P ICML WORKSH HUM IN

[4]

[Anonymous], 2017, A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop