Year: 2020
Type: article
Abstract: The pervasive adoption of Artificial Intelligence (AI) models in the modern \ninformation society, requires counterbalancing the growing decision power \ndemanded to AI models with risk assessment methodologies. In this paper, we \nconsider the risk of discriminatory decisions and review approaches for \ndiscovering discrimination and for designing fair AI models. We highlight the \ntight relations between discrimination discovery and explainable AI, with the \nlatter being a more general approach for understanding the behavior of black \nboxes.
Authors: S. Ruggieri, F. Giannotti, R. Guidotti, A. Monreale, D. Pedreschi, F. Turini
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W7033091896
