Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Certifying and Removing Disparate Impact
1.757
Zitationen
5
Autoren
2015
Jahr
Abstract
What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender) and an explicit description of the process.
Ähnliche Arbeiten
The global landscape of AI ethics guidelines
2019 · 4.791 Zit.
The Limitations of Deep Learning in Adversarial Settings
2016 · 3.893 Zit.
Trust in Automation: Designing for Appropriate Reliance
2004 · 3.543 Zit.
Fairness through awareness
2012 · 3.314 Zit.
AI4People—An Ethical Framework for a Good AI Society: Opportunities, Risks, Principles, and Recommendations
2018 · 3.268 Zit.