EuroVisPosters

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/15273

Browse

Browsing EuroVisPosters by Subject "Artificial intelligence"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A Dashboard for Interactive Convolutional Neural Network Training And Validation Through Saliency Maps
    (The Eurographics Association, 2023) Cech, Tim; Simsek, Furkan; Scheibel, Willy; Döllner, Jürgen; Gillmann, Christina; Krone, Michael; Lenti, Simone
    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.
  • Thumbnail Image
    Item
    Interactive Visualization of Machine Learning Model Results Predicting Infection Risk
    (The Eurographics Association, 2022) Schäfer, Steffen; Baumgartl, Tom; Wulff, Antje; Kuijper, Arjan; Marschollek, Michael; Scheithauer, Simone; von Landesberger, Tatiana; Krone, Michael; Lenti, Simone; Schmidt, Johanna
    We present a novel visual-interactive interface to show results of a machine learning algorithm, which predicts the infection probability for patients in hospitals. The model result data is complex and needs to be presented in a clear and intuitive way to microbiology and infection control experts in hospitals. Our visual-interactive interface offers linked views which allow for detailed analysis of the model results. Feedback from microbiology and infection control experts showed that they were able to extract new insights regarding outbreaks and transmission pathways.