A Dashboard for Interactive Convolutional Neural Network Training And Validation Through Saliency Maps
| dc.contributor.author | Cech, Tim | en_US |
| dc.contributor.author | Simsek, Furkan | en_US |
| dc.contributor.author | Scheibel, Willy | en_US |
| dc.contributor.author | Döllner, Jürgen | en_US |
| dc.contributor.editor | Gillmann, Christina | en_US |
| dc.contributor.editor | Krone, Michael | en_US |
| dc.contributor.editor | Lenti, Simone | en_US |
| dc.date.accessioned | 2023-06-10T06:31:26Z | |
| dc.date.available | 2023-06-10T06:31:26Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Quali-quantitative methods provide ways for interrogating Convolutional Neural Networks (CNN). For it, we propose a dashboard using a quali-quantitative method based on quantitative metrics and saliency maps. By those means, a user can discover patterns during the training of a CNN. With this, they can adapt the training hyperparameters of the model, obtaining a CNN that learned patterns desired by the user. Furthermore, they neglect CNNs which learned undesirable patterns. This improves users' agency over the model training process. | en_US |
| dc.description.seriesinformation | EuroVis 2023 - Posters | |
| dc.identifier.doi | 10.2312/evp.20231054 | |
| dc.identifier.isbn | 978-3-03868-220-2 | |
| dc.identifier.pages | 5-7 | |
| dc.identifier.pages | 3 pages | |
| dc.identifier.uri | https://doi.org/10.2312/evp.20231054 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/evp20231054 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies -> Artificial intelligence | |
| dc.subject | Computing methodologies | |
| dc.subject | Artificial intelligence | |
| dc.title | A Dashboard for Interactive Convolutional Neural Network Training And Validation Through Saliency Maps | en_US |