Show simple item record

dc.contributor.authorBodria, Francescoen_US
dc.contributor.authorRinzivillo, Salvatoreen_US
dc.contributor.authorFadda, Danieleen_US
dc.contributor.authorGuidotti, Riccardoen_US
dc.contributor.authorGiannotti, Foscaen_US
dc.contributor.authorPedreschi, Dinoen_US
dc.contributor.editorAgus, Marcoen_US
dc.contributor.editorAigner, Wolfgangen_US
dc.contributor.editorHoellt, Thomasen_US
dc.date.accessioned2022-06-02T15:50:46Z
dc.date.available2022-06-02T15:50:46Z
dc.date.issued2022
dc.identifier.isbn978-3-03868-184-7
dc.identifier.urihttps://doi.org/10.2312/evs.20221098
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/evs20221098
dc.description.abstractAutoencoders are a powerful yet opaque feature reduction technique, on top of which we propose a novel way for the joint visual exploration of both latent and real space. By interactively exploiting the mapping between latent and real features, it is possible to unveil the meaning of latent features while providing deeper insight into the original variables. To achieve this goal, we exploit and re-adapt existing approaches from eXplainable Artificial Intelligence (XAI) to understand the relationships between the input and latent features. The uncovered relationships between input features and latent ones allow the user to understand the data structure concerning external variables such as the predictions of a classification model. We developed an interactive framework that visually explores the latent space and allows the user to understand the relationships of the input features with model prediction.en_US
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing --> User interface design; Visualization techniques
dc.subjectHuman centered computing
dc.subjectUser interface design
dc.subjectVisualization techniques
dc.titleExplaining Black Box with Visual Exploration of Latent Spaceen_US
dc.description.seriesinformationEuroVis 2022 - Short Papers
dc.description.sectionheadersVisual Analysis and Machine Learning
dc.identifier.doi10.2312/evs.20221098
dc.identifier.pages85-89
dc.identifier.pages5 pages


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License