Bilde av Wickstrøm, Kristoffer
Bilde av Wickstrøm, Kristoffer
Førsteamanuensis / Maskinlæring Institutt for fysikk og teknologi kristoffer.k.wickstrom@uit.no +4777623216 Her finner du meg

Kristoffer Wickstrøm


Stillingsbeskrivelse

Jeg er førsteamanuensis i Maskinlæringsgruppa ved UiT Norges arktiske universitet og forskningsleder for tolkbarhet i SFI Visual Intelligence. Mitt hovedforskningsområde er dyp læring, med særlig fokus på forklarbarhet og læring med begrensede data. Jeg er også interessert i usikkerhetsmodellering, informasjonsteori, kjernemetoder og medisinsk bildeanalyse. Jeg har tidligere vært gjesteforsker i bildebehandlingslaboratoriet ved Universitetet i Valencia med professor Gustau Camps-Valls og i Understandable Machine Intelligence Laboratory ved Technical University of Berlin med professor Marina M.-C. Höhne.

Se Google Scholar for en liste over mine publikasjoner.


  • Bjørn Møller, Christian Igel, Kristoffer Knutsen Wickstrøm, Jon Sporring, Robert Jenssen, Bulat Ibragimov :
    Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks
    International Conference on Learning Representations 2024
  • Kristoffer Wickstrøm, Daniel Johansen Trosten, Sigurd Eivindson Løkse, Ahcene Boubekki, Karl Øyvind Mikalsen, Michael Kampffmeyer m.fl.:
    RELAX: Representation Learning Explainability
    International Journal of Computer Vision 2023 ARKIV / DOI
  • Daniel Johansen Trosten, Rwiddhi Chakraborty, Sigurd Eivindson Løkse, Kristoffer Wickstrøm, Robert Jenssen, Michael Kampffmeyer :
    Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings
    Computer Vision and Pattern Recognition 2023 ARKIV / DOI
  • Kristoffer Wickstrøm, Sigurd Eivindson Løkse, Michael Kampffmeyer, Shujian Yu, José C. Príncipe, Robert Jenssen :
    Analysis of Deep Convolutional Neural Networks Using Tensor Kernels and Matrix-Based Entropy
    Entropy 2023 ARKIV / DOI
  • Eirik Agnalt Østmo, Kristoffer Wickstrøm, Keyur Radiya, Michael Kampffmeyer, Robert Jenssen :
    View it like a radiologist: Shifted windows for deep learning augmentation of CT images
    Machine Learning for Signal Processing 2023 ARKIV / DOI
  • Kristoffer Wickstrøm, Eirik Agnalt Østmo, Keyur Radiya, Karl Øyvind Mikalsen, Michael Kampffmeyer, Robert Jenssen :
    A clinically motivated self-supervised approach for content-based image retrieval of CT liver images
    Computerized Medical Imaging and Graphics 2023 ARKIV / DOI
  • Ane Blazquez-Garcia, Kristoffer Knutsen Wickstrøm, Shujian Yu, Karl Øyvind Mikalsen, Ahcene Boubekki, Angel Conde m.fl.:
    Selective Imputation for Multivariate Time Series Datasets with Missing Values
    IEEE Transactions on Knowledge and Data Engineering 2023 ARKIV / DOI
  • Kristoffer Knutsen Wickstrøm, Marina Marie-Claire Höhne :
    The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus
    Transactions on Machine Learning Research (TMLR) 2023 ARKIV
  • Kristoffer Wickstrøm, Michael Kampffmeyer, Karl Øyvind Mikalsen, Robert Jenssen :
    Mixing up contrastive learning: Self-supervised representation learning for time series
    Pattern Recognition Letters 2022 ARKIV / DOI
  • Andreas Kvammen, Kristoffer Wickstrøm, Samuel Kociscak, Jakub Vaverka, Libor Nouzak, Arnaud Zaslavsky m.fl.:
    Machine learning detection of dust impact signals observed by the Solar Orbiter
    Annales Geophysicae 2022 DATA / ARKIV / DOI
  • Kristoffer Wickstrøm, Juan Emmanuel Johnson, Sigurd Eivindson Løkse, Gusatu Camps-Valls, Karl Øyvind Mikalsen, Michael Kampffmeyer m.fl.:
    The Kernelized Taylor Diagram
    Communications in Computer and Information Science (CCIS) 2022 ARKIV / DOI
  • Samuel Kuttner, Kristoffer Knutsen Wickstrøm, Mark Lubberink, Andreas Tolf, Joachim Burman, Rune Sundset m.fl.:
    Cerebral blood flow measurements with 15O-water PET using a non-invasive machine-learning-derived arterial input function
    Journal of Cerebral Blood Flow and Metabolism 08. februar 2021 ARKIV / DOI
  • Kristoffer Knutsen Wickstrøm, Karl Oyvind Mikalsen, Michael Kampffmeyer, Arthur Revhaug, Robert Jenssen :
    Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
    IEEE Journal of Biomedical and Health Informatics 2021 ARKIV / DOI
  • Samuel Kuttner, Kristoffer Knutsen Wickstrøm, Gustav Kalda, Seyed Esmaeil Dorraji, Montserrat Martin-Armas, Ana Oteiza m.fl.:
    Machine learning derived input-function in a dynamic 18F-FDG PET study of mice
    Biomedical Engineering & Physics Express 2020 ARKIV / DOI
  • Shujian Yu, Kristoffer Knutsen Wickstrøm, Robert Jenssen, Jose Principe :
    Understanding Convolutional Neural Networks With Information Theory: An Initial Exploration
    IEEE Transactions on Neural Networks and Learning Systems 2020 DOI
  • Andreas Kvammen, Kristoffer Knutsen Wickstrøm, Derek McKay, Noora Partamies :
    Auroral Image Classification With Deep Neural Networks
    Journal of Geophysical Research (JGR): Space Physics 05. oktober 2020 ARKIV / DOI
  • Kristoffer Knutsen Wickstrøm, Michael C. Kampffmeyer, Robert Jenssen :
    Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps
    Medical Image Analysis 2019 ARKIV / DOI
  • Kristoffer Knutsen Wickstrøm, Michael C. Kampffmeyer, Robert Jenssen :
    Uncertainty modeling and interpretability in convolutional neural networks for polyp segmentation
    IEEE Signal Processing Society 2018 ARKIV / DOI
  • Robert Jenssen, Kristoffer Knutsen Wickstrøm, Petter Bjørklund :
    Slik kan kunstig intelligens hjelpe legene
    Forskning.no 2024
  • Kristoffer Knutsen Wickstrøm :
    Kunstig intelligens fra beslutningstøtte til beslutningstaker – hvem er ansvarlig når ting går galt?
    2024
  • Christian Salomonsen, Kristoffer Knutsen Wickstrøm, Elisabeth Wetzer, Samuel Kuttner :
    Kinetic modeling based compound loss for deep learning derived input function prediction in dynamic [18F]FDG PET images of mice
    2024
  • Christian Salomonsen, Kristoffer Knutsen Wickstrøm, Elisabeth Wetzer, Samuel Kuttner :
    Kinetic modeling based compound loss for deep learning derived input function prediction in dynamic [18F]FDG PET images of mice
    2024
  • Christian Salomonsen, Kristoffer Knutsen Wickstrøm, Elisabeth Wetzer, Samuel Kuttner :
    Kinetic modeling based compound loss for deep learning derived input function prediction in dynamic [18F]FDG PET images of mice
    2024
  • Petter Bjørklund, Kristoffer Knutsen Wickstrøm, Keyur Radiya :
    Finner leverkreft med kunstig intelligens
    uit.no 2024
  • Kristoffer Knutsen Wickstrøm, Keyur Radiya :
    Finner leverkreft med kunstig intelligens
    uit.no 2024
  • Kristoffer Knutsen Wickstrøm :
    Facebook skal merke KI-bilder: – Stor nyhet
    07. februar 2024
  • Kristoffer Knutsen Wickstrøm :
    Morrasendinga fra NRK i Troms - Forskere ved UiT Norges arktiske universitet utvikler kunstig intelligens til å finne leverkreft.
    10. juni 2024
  • Kristoffer Knutsen Wickstrøm :
    Kunstig Intelligens, utfordringer og muligheter for næringslivet
    2024
  • Lars Uebbing, Harald Lykke Joakimsen, Luigi Tommaso Luppino, Iver Martinsen, Andrew McDonald, Kristoffer Knutsen Wickstrøm m.fl.:
    Investigating the Impact of Feature Reduction for Deep Learning-based Seasonal Sea Ice Forecasting
    2024
  • Kristoffer Knutsen Wickstrøm :
    Muligheter og utfordringer for kunstig intelligens i næringslivet
    2024
  • Kristoffer Knutsen Wickstrøm :
    Forskningsfronten på kunstig intelligens
    2024
  • Petter Bjørklund, Robert Jenssen, Kristoffer Knutsen Wickstrøm :
    KI har superkrefter som kan hjelpe legene våre
    uit.no 2024
  • Andreas Kvammen, Kristoffer Wickstrøm, Samuel Kociscak, Jakub Vaverka, Libor Nouzák, Arnaud Zaslavsky m.fl.:
    Machine learning detection of dust impact signals
    2023
  • Kristoffer Wickstrøm :
    The aggregation method matters in faithfulness evaluation of XAI
    2023
  • Robert Jenssen, Kristoffer Knutsen Wickstrøm :
    Ja takk til «krysskulturelle» prosjekter drevet fram av teknologiutvikling
    Khrono.no 2023
  • Robert Jenssen, Kristoffer Knutsen Wickstrøm :
    Hvordan bør fotavtrykket av regjeringens satsing på kunstig intelligens se ut i Nord-Norge i 2030?
    Nordnorsk Debatt 2023
  • Kristoffer Knutsen Wickstrøm :
    XAI for time series analysis
    2023
  • Kristoffer Knutsen Wickstrøm :
    XAI for understanding of SSL representations
    2023
  • Kristoffer Knutsen Wickstrøm, Daniel Johansen Trosten, Sigurd Eivindson Løkse, Karl Øyvind Mikalsen, Michael Kampffmeyer, Robert Jenssen :
    RELAX: Representation Learning Explainability
    2022
  • Daniel Johansen Trosten, Kristoffer Wickstrøm, Shujian Yu, Sigurd Eivindson Løkse, Robert Jenssen, Michael Kampffmeyer :
    Deep Clustering with the Cauchy-Schwarz Divergence
    2022
  • Kristoffer Wickstrøm :
    Advancing Deep Learning with Emphasis on Data-Driven Healthcare
    UiT Norges arktiske universitet 2022
  • Kristoffer Wickstrøm :
    The past, present, and future of XAI
    2022
  • Kristoffer Wickstrøm, Eirik Agnalt Østmo, Karl Øyvind Mikalsen, Michael Kampffmeyer, Robert Jenssen :
    Explaining representations for medical image retrieval
    2022
  • Samuel Kuttner, Luigi Tommaso Luppino, Kristoffer Wickstrøm, Nils Thomas Doherty Midtbø, Seyed Esmaeil Dorraji, Ana Oteiza m.fl.:
    Deep learning derived input function in dynamic 18F-FDG PET imaging of mice
    2022
  • Kristoffer Wickstrøm, Juan Emmanuel Johnson, Sigurd Eivindson Løkse, Gusatu Camps-Valls, Karl Øyvind Mikalsen, Michael Kampffmeyer m.fl.:
    The Kernelized Taylor Diagram
    2022
  • Kristoffer Wickstrøm :
    Hva gjør vi når kunstig intelligens gir oss kunnskap vi ikke forstår?
    Forskersonen.no 03. januar 2022
  • Kristoffer Wickstrøm :
    Technical aspects of translating AI algorithms into real life medical practice, within the design and implementation of Randomized Controlled Trials
    2022
  • Kristoffer Knutsen Wickstrøm, Sigurd Eivindson Løkse, Karl Øyvind Mikalsen, Michael Kampffmeyer, Robert Jenssen :
    Towards Explainable Representation Learning
    2021
  • Kristoffer Knutsen Wickstrøm, Karl Øyvind Mikalsen, Michael Kampffmeyer, Arthur Revhaug, Robert Jenssen :
    Uncertainty-Aware Deep Ensembles for Explainable Time Series Prediction
    2021
  • Kristoffer Knutsen Wickstrøm, Michael Kampffmeyer, Robert Jenssen :
    Advances in explainable DL & how to model uncertainty in explainability
    2021

  • De 50 siste resultatene fra Cristin vises på siden. Se alle arbeider i Cristin her →


    Forskningsinteresser

    Dyp læring.
    Tolkbar kunstig intelligens.
    Usikkerhetsanalyse.
    Medisinsk bildeanalyse.
    Læring med begrenset data.


    Medlem i forskningsgruppe