State of the Art of Visual Analytics for eXplainable Deep Learning

Simple item page
dc.contributor.authorLa Rosa, B.en_US
dc.contributor.authorBlasilli, G.en_US
dc.contributor.authorBourqui, R.en_US
dc.contributor.authorAuber, D.en_US
dc.contributor.authorSantucci, G.en_US
dc.contributor.authorCapobianco, R.en_US
dc.contributor.authorBertini, E.en_US
dc.contributor.authorGiot, R.en_US
dc.contributor.authorAngelini, M.en_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2023-03-22T15:07:15Z
dc.date.available2023-03-22T15:07:15Z
dc.date.issued2023
dc.description.abstractThe use and creation of machine‐learning‐based solutions to solve problems or reduce their computational costs are becoming increasingly widespread in many domains. Deep Learning plays a large part in this growth. However, it has drawbacks such as a lack of explainability and behaving as a black‐box model. During the last few years, Visual Analytics has provided several proposals to cope with these drawbacks, supporting the emerging eXplainable Deep Learning field. This survey aims to (i) systematically report the contributions of Visual Analytics for eXplainable Deep Learning; (ii) spot gaps and challenges; (iii) serve as an anthology of visual analytical solutions ready to be exploited and put into operation by the Deep Learning community (architects, trainers and end users) and (iv) prove the degree of maturity, ease of integration and results for specific domains. The survey concludes by identifying future research challenges and bridging activities that are helpful to strengthen the role of Visual Analytics as effective support for eXplainable Deep Learning and to foster the adoption of Visual Analytics solutions in the eXplainable Deep Learning community. An interactive explorable version of this survey is available online at .en_US
dc.description.documenttypestar
dc.description.number1
dc.description.sectionheadersMajor Revision from EuroVis Symposium
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14733
dc.identifier.issn1467-8659
dc.identifier.pages319-355
dc.identifier.urihttps://doi.org/10.1111/cgf.14733
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14733
dc.publisherEurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.rightsCC BY-NC Attribution-NonCommercial 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/
dc.subjectdeep learning
dc.subjectexplainable artificial intelligence
dc.subjectinterpretability
dc.subjectneural networks
dc.subjectvisual analytics
dc.subjectvisualization
dc.titleState of the Art of Visual Analytics for eXplainable Deep Learningen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v42i1pp319-355-cgf14733.pdf
Size:
3.98 MB
Format:
Adobe Portable Document Format
Download
Collections
42-Issue 1