Cech, TimSimsek, FurkanScheibel, WillyDöllner, JürgenGillmann, ChristinaKrone, MichaelLenti, Simone2023-06-102023-06-102023978-3-03868-220-2https://doi.org/10.2312/evp.20231054https://diglib.eg.org:443/handle/10.2312/evp20231054Quali-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.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies -> Artificial intelligenceComputing methodologiesArtificial intelligence10.2312/evp.202310545-73 pages