Cybertrust: From Explainable to Actionable and Interpretable Artificial Intelligence

Igor Linkov; Stephanie Galaitsi; Benjamin D. Trump; Jeffrey M. Keisler; Alexander Kott

doi:10.1109/MC.2020.2993623

Cybertrust: From Explainable to Actionable and Interpretable Artificial Intelligence

Igor Linkov
, Stephanie Galaitsi
, Benjamin D. Trump
, Jeffrey M. Keisler
, Alexander Kott

Management Science & Information Systems

United States Army
University of Massachusetts Boston
U.S. Army Futures Command

Research output: Contribution to specialist publication › Article

Abstract

We argue that artificial intelligence (AI) systems should be designed with features that build trust by bringing decision-analytic perspectives into AI. Actionable and interpretable AI will incorporate explicit quantifications and visualizations of user confidence in AI recommendations.

Original language	English
Pages	91-96
Number of pages	6
Volume	53
No	9
Specialist publication	Computer
DOIs	https://doi.org/10.1109/MC.2020.2993623
State	Published - Sep 2020

ASJC Scopus Subject Areas

General Computer Science

Access to Document

10.1109/MC.2020.2993623

Cite this

@misc{ddfdae8b7cfc4831b3a471caf37e2ec2,

title = "Cybertrust: From Explainable to Actionable and Interpretable Artificial Intelligence",

abstract = "We argue that artificial intelligence (AI) systems should be designed with features that build trust by bringing decision-analytic perspectives into AI. Actionable and interpretable AI will incorporate explicit quantifications and visualizations of user confidence in AI recommendations.",

author = "Igor Linkov and Stephanie Galaitsi and Trump, \{Benjamin D.\} and Keisler, \{Jeffrey M.\} and Alexander Kott",

note = "Publisher Copyright: {\textcopyright} 1970-2012 IEEE.",

year = "2020",

month = sep,

doi = "10.1109/MC.2020.2993623",

language = "English",

volume = "53",

pages = "91--96",

journal = "Computer",

issn = "0018-9162",

publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Cybertrust

T2 - From Explainable to Actionable and Interpretable Artificial Intelligence

AU - Linkov, Igor

AU - Galaitsi, Stephanie

AU - Trump, Benjamin D.

AU - Keisler, Jeffrey M.

AU - Kott, Alexander

PY - 2020/9

Y1 - 2020/9

N2 - We argue that artificial intelligence (AI) systems should be designed with features that build trust by bringing decision-analytic perspectives into AI. Actionable and interpretable AI will incorporate explicit quantifications and visualizations of user confidence in AI recommendations.

AB - We argue that artificial intelligence (AI) systems should be designed with features that build trust by bringing decision-analytic perspectives into AI. Actionable and interpretable AI will incorporate explicit quantifications and visualizations of user confidence in AI recommendations.

UR - https://www.scopus.com/pages/publications/85091140357

UR - https://www.scopus.com/pages/publications/85091140357#tab=citedBy

U2 - 10.1109/MC.2020.2993623

DO - 10.1109/MC.2020.2993623

M3 - Article

AN - SCOPUS:85091140357

SN - 0018-9162

VL - 53

SP - 91

EP - 96

JO - Computer

JF - Computer

ER -

Cybertrust: From Explainable to Actionable and Interpretable Artificial Intelligence

Abstract

ASJC Scopus Subject Areas

Access to Document

Other files and links

Fingerprint

Cite this