• Sparse Neural Network Interpretability: A Comparative Analysis of Au toencoders and Transformers 

  Iversen, Sebastian Tendstrand (Master thesis, 2025)

  As neural networks grow increasingly complex and powerful, understanding their internal representations becomes critical for ensuring safe and reliable AI systems. This thesis addresses a fundamental challenge in mechanistic interpretability: how architectural choices in sparse representation learning shape our ability to understand neural network internals. We present the first comprehensive ...
• Using Self-Supervised Learning To Improve Deep Learning-Based Analysis of 4D PET Imaging 

  Johannessen, Ruben Andre Hanssen (Master thesis, 2025)

  Dynamic positron emission tomography (dPET) imaging requires an accurate arterial input function (AIF) for quantitative analysis. However, traditional methods for AIF measurement require invasive blood sampling. Recent deep learning models can predict the AIF from the 4D PET data itself, eliminating the need for invasive blood sampling. However, their performance often degrades with limited amount ...
• Utsteders erstatningsansvar overfor aksjetegner for uriktig informasjon i prospekt ved emisjon 

  Moen, Marie Helen (Master thesis, 2025)

  Oppgavens tema er utsteders erstatningsansvar overfor aksjetegner for tap som skyldes uriktig informasjon i prospekt, etter registering av emisjonen i Foretaksregisteret. Oppgaven er skrevet med et kritisk blikk på «Labogas-regelen» og allmennaksjeloven § 2-10 andre ledd, jf. § 10-7 tredje ledd.
• Oil spills, lookalikes and a whole lot of noise: A diffusion based approach for Oil Spill Detection in SAR Images 

  Hanssen, Sigurd Almli (Master thesis, 2025)

  Accurate and fast oil spill detection is crucial to enable effective usage of mitigation resources to minimize environmental damage. Synthetic Aperture Radar (SAR) imagery provides a reliable means of large-scale ocean monitoring, but analyzing these images remains a time-consuming and labor-intensive task. The presence of lookalikes in SAR images, natural phenomena imitating the appearance of oil ...
• 

  Late Holocene history of Sefströmbreen in Ekmanfjorden, Svalbard 

  Jahnsen, Mathilde Lyford (Master thesis, 2025)

  There is limited documentation of complete surge cycles from Svalbard. Since the Little Ice Age, multiple surge-type glaciers in Svalbard have been undergoing continuous retreat. This has led to the formation of combined terrestrial and marine terminating margins, as well as newly exposed terrain, featuring glacial landforms such as crevasse-squeeze ridges, which are diagnostic landforms of surge-type ...

View more