On the Rationality of Explanations in Classification Algorithms
![Thumbnail](/xmlui/bitstream/handle/10234/200901/Zoe_Falomir_Rationality.pdf.jpg?sequence=4&isAllowed=y)
Visualitza/
Metadades
Mostra el registre complet de l'elementcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/61544
comunitat-uji-handle4:
INVESTIGACIONMetadades
Títol
On the Rationality of Explanations in Classification AlgorithmsData de publicació
2021Editor
IOS PressISBN
9781643682112; 9781643682105Tipus de document
info:eu-repo/semantics/bookPartVersió de l'editorial
https://ebooks.iospress.nl/doi/10.3233/FAIA210165Versió
info:eu-repo/semantics/publishedVersionParaules clau / Matèries
Resum
This paper is a first step towards studying the rationality of explanations produced by up-to-date AI systems. Based on the thesis that designing rational explanations for accomplishing trustworthy AI is fundamental ... [+]
This paper is a first step towards studying the rationality of explanations produced by up-to-date AI systems. Based on the thesis that designing rational explanations for accomplishing trustworthy AI is fundamental for ethics in AI, we study the rationality criteria that explanations in classification algorithms have to meet. In this way, we identify, define, and exemplify characteristic criteria of rational explanations in classification algorithms. [-]
Publicat a
Artificial Intelligence Research and Development M. Villaret et al. (Eds.), Amsterdam, Netherlands : IOS Press , 2021Entitat finançadora
Ministerio de Ciencia e Innovación. Ramon y Cajal
Codi del projecte o subvenció
RYC2019-027177-I/AEI/10.13039/501100011033
Drets d'accés
info:eu-repo/semantics/openAccess