Below find selected publications, talks, and reviewing activities by me. More details about my publications at my ORCID or Google Scholar profiles.

Selected PublicationsORCID iD icon0000-0003-2690-2478

  • Mikriukov, Georgii, Gesina Schwalbe, Christian Hellert, and Korinna Bade. 2023. “Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability“. In Proc. 1st World Conf. eXplainable Artificial Intelligence. Springer. https://arxiv.org/abs/2304.14864. (Best Industry Paper Award)
  • Schwalbe, Gesina, and Bettina Finzel. 2023. “A comprehensive taxonomy for explainable artificial intelligence: A systematic survey of surveys on methods and concepts.” Data Mining and Knowledge Discovery, pp. 1-59. https://doi.org/10.1007/s10618-022-00867-8.
  • Schwalbe, Gesina, Christian Wirth, and Ute Schmid. 2022. “Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings.” Preprint. https://arxiv.org/abs/2201.00572.
  • Schwalbe, Gesina. 2021. “Verification of Size Invariance in DNN Activations Using Concept Embeddings.” In AIAI 2021: Artificial Intelligence Applications and Innovations. IFIP Advances in Information and Communication Technology. Springer. https://doi.org/10.1007/978-3-030-79150-6_30. (arXiv:2105.06727)
  • Rabold, Johannes, Gesina Schwalbe, and Ute Schmid. 2020. “Expressive Explanations of DNNs by Combining Concept Analysis with ILP.” In KI 2020: Advances in Artificial Intelligence, 148–62. Lecture Notes in Computer Science. Springer International Publishing. https://doi.org/10.1007/978-3-030-58285-2_11. (arXiv:2105.07371)
  • Schwalbe, Gesina. 2020. “A Survey on Methods for the Safety Assurance of Machine Learning Based Systems.” In Proc. 10th European Congress Embedded Real Time Software and Systems. Toulouse, France. (hal-02442819)
  • Schwalbe, Gesina, Bernhard Knie, Timo Sämann, Timo Dobberphul, Lydia Gauerhof, Shervin Raafatnia, and Vittorio Rocco. 2020. “Structuring the Safety Argumentation for Deep Neural Network Based Perception in Automotive Applications.” In Computer Safety, Reliability, and Security. SAFECOMP 2020 Workshops, 383–394. Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-55583-2_29 (preprint on ResearchGate).

Selected Talks

Machine Learning

  • Schwalbe, Gesina. 2022. “Diversity and Applications of Explainable Artificial Intelligence Methods.” Presented at the Women in Data Science Regensburg 2022 (WiDS’22), Regensburg, Germany, April 14. https://www.wids-regensburg.de/wids-regensburg-2022/. recording.
  • Schwalbe, Gesina. 2021. “Methods & Challenges for the Safety Assurance of Deep Neural Networks in Computer Vision.” Presented at the Women in Data Science Regensburg 2021 (WiDS’21), Regensburg, Germany, April 14. https://sites.google.com/view/widsregensburg.
  • Schwalbe, Gesina, and Jing Xiao. 2019. “Safety Argument for ML Based Systems in the Context of Highly Automated Driving.” Presented at the 9th VDA Automotive SYS Conference, Potsdam, Germany, June 27.

Mathematics

All official material (theses, term papers, and talks) is linked in this Github repository.

Other

  • 2023-04-27 “Pedestrian Detection in Automated Driving”. (German). Talk at Girls’ Day of the University of Bamberg 2023.
  • 2019-09-04 “From Mathematics to PhD Student in Machine Learning”. (German). Informative talk at trial studies mathematics 2019.
  • 2016-06-11 “An Insight into Typography”. (German). Informative talk on a selection of typographical topics at privately organized Seminar. (slides)

Invited Reviews