On the Rationality of Explanations in Classification Algorithms
![Thumbnail](/xmlui/bitstream/handle/10234/200901/Zoe_Falomir_Rationality.pdf.jpg?sequence=4&isAllowed=y)
View/ Open
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/61544
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
On the Rationality of Explanations in Classification AlgorithmsDate
2021Publisher
IOS PressISBN
9781643682112; 9781643682105Type
info:eu-repo/semantics/bookPartPublisher version
https://ebooks.iospress.nl/doi/10.3233/FAIA210165Version
info:eu-repo/semantics/publishedVersionSubject
Abstract
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. [-]
Is part of
Artificial Intelligence Research and Development M. Villaret et al. (Eds.), Amsterdam, Netherlands : IOS Press , 2021Funder Name
Ministerio de Ciencia e Innovación. Ramon y Cajal
Project code
RYC2019-027177-I/AEI/10.13039/501100011033
Rights
info:eu-repo/semantics/openAccess