Skip to main content
Journal ArticleOPEN ACCESS

Detecting Systematic Deviations in Data and Models

Computer (2023) 56(2) 82-92
DOI: 10.1109/MC.2022.3213209
3Citations
Citations of this article
10Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

Trustworthy artificial intelligence researchers should seek to better detect and characterize systematic deviations in data and models (that is, bias). This article provides data scientists with motivation, theory, code, and examples on how to perform disciplined discovery of systematic deviations in data and models at the subset level.

Cite

CITATION STYLE

APA

Speakman, S., Tadesse, G. A., Cintas, C., Ogallo, W., Akumu, T., & Oshingbesan, A. (2023). Detecting Systematic Deviations in Data and Models. Computer, 56(2), 82–92. https://doi.org/10.1109/MC.2022.3213209

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free