Krug

Wiss. Mitarbeiter/-in

Dr.-Ing. Valerie Krug

Institut für Intelligente Kooperierende Systeme (IKS)
AG Artificial Intelligence Lab
Universitätsplatz 2, Gebäude 29, 39106 Magdeburg, G29-024
About me

Education

  • 2010 - 2013: Bachelor of Science "Biotechnology/Bioinformatics", Mittweida University of Applied Sciences
  • 2013 - 2016: Master of Science "Bioinformatics", University of Potsdam
  • 2016 - 2019: Researcher/PhD student at the Machine Learning in Cognitive Science Lab, University of Potsdam
  • 2019 - 2024: Researcher/PhD student at the AI Lab, OVGU
  • Since 2024: Postdoctoral Researcher at the AI Lab, OVGU

Main Research Focus

  • explainable Artificial Intelligence (XAI)
  • analyzing and visualizing Deep Learning models (aka Introspection)

Further Interests

  • visualizing and communicating science
    (e.g. for exhibits, public talks)

Selected Publications:

  • Visualizing Deep Neural Networks with Topographic Activation Maps.
    Valerie Krug; Raihan Kabir Ratul; Christopher Olson & Sebastian Stober.
    In HHAI 2023: Augmenting Human Intellect. IOS Press, 2023. 138-152.
    [URL] [github]
  • Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles.
    Valerie Krug; Maral Ebrahimzadeh; Jost Alemann; Jens Johannsmeier & Sebastian Stober.
    In: Electronics 10 (11), 1350, 2021.
    [URL]
  • Visualizing Deep Neural Networks for Speech Recognition with Learned Topographic Filter Maps.
    Valerie Krug & Sebastian Stober.
    In: Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2019.
  • Neuron Activation Profiles for Interpreting Convolutional Speech Recognition Models.
    Valerie Krug; René Knaebel & Sebastian Stober.
    In: NeurIPS 2018 Interpretability and Robustness for Audio, Speech and Language Workshop (IRASL’18), 2018.

Courses

Below, you can see the classes I'm currently involved in.

Last Modification: 22.02.2024 - Contact Person: Webmaster