Blar i HVL Open på forfatter "Sagemüller, Justus"

Viser treff 1-3 av 3

    • Ablation Path Saliency 

      Sagemüller, Justus; Verdier, Olivier Philippe Paul (Peer reviewed; Journal article, 2023)
      Various types of saliency methods have been proposed for explaining black-box classification. In image applications, this means highlighting the part of the image that is most relevant for the current decision. Unfortunately, ...

    • Paths towards reliable explainability: In neural networks for image-processing 

      Sagemüller, Justus (Doctoral thesis, 2024)
      Machine learning systems (often referred to as AI, not always appropriately) are increasingly used in varied applications, including ones with strong impact on human lives. While this is expected to bring economic and ...

    • Proceedings of the PhD Symposium at iFM’19on Formal Methods: Algorithms, Tools and Applications (PhD-iFM’19) 

      Pun, Ka I; Stolz, Volker; Fazeldehkordi, Elahe; Owe, Olaf; Ramezanifarkhani, Toktam; Damasceno, Carlos Diego Nascimento; Damasceno, Carlos Diego Nascimento; Ahishakiye, Faustin; Kristensen, Lars Michael; Tabar, Asmae Heydari; Bubel, Richard; Hähnle, Reiner; Sagemüller, Justus; Verdier, Olivier (HVL-rapport;14/2020, Report, 2020)
      Preface: This research report contains the proceedings of the PhD Symposium at iFM’19 on Formal Methods: Algorithms, Tools and Applications (PhD-iFM’19), which was held on 3 December, 2019 at Western Norway ...