%0 Conference Proceedings
%T New Frontiers in Explainable AI: Understanding the GI to Interpret the GO
%+ Università degli Studi di Milano-Bicocca = University of Milano-Bicocca (UNIMIB)
%+ IRCCS Istituto Ortopedico Galeazzi
%A Cabitza, Federico
%A Campagner, Andrea
%A Ciucci, Davide
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 3rd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE)
%C Canterbury, United Kingdom
%Y Andreas Holzinger
%Y Peter Kieseberg
%Y A Min Tjoa
%Y Edgar Weippl
%I Springer International Publishing
%3 Machine Learning and Knowledge Extraction
%V LNCS-11713
%P 27-47
%8 2019-08-26
%D 2019
%R 10.1007/978-3-030-29726-8_3
%K Ground truth
%K Explainable AI
%K Reliability
%K Usable AI
%Z Computer Science [cs]Conference papers
%X In this paper we focus on the importance of interpreting the quality of the input of predictive models (potentially a GI, i.e., a Garbage In) to make sense of the reliability of their output (potentially a GO, a Garbage Out) in support of human decision making, especially in critical domains, like medicine. To this aim, we propose a framework where we distinguish between the Gold Standard (or Ground Truth) and the set of annotations from which this is derived, and a set of quality dimensions that help to assess and interpret the AI advice: fineness, trueness, representativeness, conformity, dryness. We then discuss implications for obtaining more informative training sets and for the design of more usable Decision Support Systems.
%G English
%Z TC 5
%Z TC 12
%Z WG 8.4
%Z WG 8.9
%Z WG 12.9
%2 https://inria.hal.science/hal-02520038/document
%2 https://inria.hal.science/hal-02520038/file/485369_1_En_3_Chapter.pdf
%L hal-02520038
%U https://inria.hal.science/hal-02520038
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-TC12
%~ IFIP-WG8-4
%~ IFIP-WG8-9
%~ IFIP-CD-MAKE
%~ IFIP-WG12-9
%~ IFIP-LNCS-11713