Cargando…
Justificatory explanations in machine learning: for increased transparency through documenting how key concepts drive and underpin design and engineering decisions
Given the pervasiveness of AI systems and their potential negative effects on people’s lives (especially among already marginalised groups), it becomes imperative to comprehend what goes on when an AI system generates a result, and based on what reasons, it is achieved. There are consistent technica...
Autores principales: | Casacuberta, David, Guersenzvaig, Ariel, Moyano-Fernández, Cristian |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer London
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8965536/ https://www.ncbi.nlm.nih.gov/pubmed/35370366 http://dx.doi.org/10.1007/s00146-022-01389-z |
Ejemplares similares
-
Justificatory explanations: a step beyond explainability in machine learning
por: Guersenzvaig, A, et al.
Publicado: (2023) -
“Blessed by the algorithm”: Theistic conceptions of artificial intelligence in online discourse
por: Singler, Beth
Publicado: (2020) -
Machine learning in bail decisions and judges’ trustworthiness
por: Morin-Martel, Alexis
Publicado: (2023) -
Exploring the roles of trust and social group preference on the legitimacy of algorithmic decision-making vs. human decision-making for allocating COVID-19 vaccinations
por: Lünich, Marco, et al.
Publicado: (2022) -
AI under great uncertainty: implications and decision strategies for public policy
por: Nordström, Maria
Publicado: (2021)