Fabian Stieler M.Sc.

Wiss. Mitarbeiter

Professur für Softwaremethodik für verteilte Systeme

Telefon:	+49 821 598-2471
E-Mail:	fabian.stieler@informatik.uni-augsburg.de
Raum:	3005 (N)
Adresse:	Universitätsstraße 6a, 86159 Augsburg

Kontakt (.vcf)

Kurzlebenslauf

2017: Bachelor of Science, Wirtschaftsinformatik
2019: Master of Science, Informatik & Informationswirtschaft

Forschungsbereiche

Machine Learning Operations (MLOps)
Explainable Artificial Intelligence (XAI)
Active Learning (AL)

Abschlussarbeiten

Reduktion des Annotationsaufwands - Ein Vergleich von Active Learning Frameworks (Bachelorarbeit)
Bias Detection using Interpretable Machine Learning Methods (Bachelorarbeit)
Evaluating Explainability in the Context of Active Learning (Masterarbeit)
Interpretierbares Maschinelles Lernen mit EKG Daten (Bachelorarbeit)
Model Explanations as Quality Gate in Machine Learning Pipelines (Masterarbeit)

Projekte

Publikationen

2023 | 2022 | 2021 | 2020 | 2018 | 2017

2023
Fabian Stieler and Bernhard Bauer. 2023. Git workflow for active learning - a development methodology proposal for data-centric AI projects. In Hermann Kaindl, Mike Mannion, Leszek Maciaszek (Eds.). Proceedings of the 18th International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE 2023), April 24-25, 2023, in Prague, Czech Republic. SciTePress, Setúbal, 202-213 DOI: 10.5220/0011988400003464 PDF \| BibTeX \| RIS \| DOI
Fabian Stieler, Miriam Elia, Benjamin Weigell, Bernhard Bauer, Peter Kienle, Anton Roth, Gregor Müllegger, Marius Nann and Sarah Dopfer. 2023. LIFEDATA - a framework for traceable active learning projects. In Kurt Schneider, Fabiano Dalpiaz, Jennifer Horkoff (Eds.). 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW), 4-5 September 2023, Hannover, Germany. IEEE, Piscataway, NJ, 465-474 DOI: 10.1109/REW57809.2023.00088 PDF \| BibTeX \| RIS \| DOI
Miriam Elia, Tobias Peter, Fabian Stieler, Bernhard Bauer, Sandra Nagl, Alanna Ebigbo and Vivien Grünherz. in press. Precision medicine for achalasia diagnosis: a multi-modal and interdisciplinary approach for training data generation [Abstract]. In IEEE - ISBI 2023: International Symposium on Biomedical Imaging, Cartagena de Indias, Colombia, April 18-21, 2023. IEEE, Piscataway, NJ PDF \| BibTeX \| RIS \| URL
2022
Fabian Stieler, Marius Nann and Bernhard Bauer. 2022. Vertrauenswürdige KI in der Medizin - von effizienter Datenannotation bis intuitiver Modellerklärung. In KI-Fabrigk @WIKOIN22, Ingolstadt, 30. Juni 2022. BibTeX \| RIS
2021
Fabian Stieler, Fabian Rabe and Bernhard Bauer. 2021. Towards domain-specific explainable AI: model interpretation of a skin image classifier using a human approach. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2021, 19-25 June 2021, Nashville, TN, USA. IEEE, Piscataway, NJ, 1802-1809 DOI: 10.1109/CVPRW53098.2021.00199 PDF \| BibTeX \| RIS \| DOI
2020
Fabian Stieler, Fabian Rabe and Bernhard Bauer. 2020. Federated medical data - how much can deep learning models benefit? [Poster]. In AMIA 2020 Virtual Clinical Informatics Converence, May 19-21. PDF \| BibTeX \| RIS
2018
Harald Schmidbauer, Angi Rösch and Fabian Stieler. 2018. Patterns of interest in industrial brands: Instagram media uploads and sentiment. In Len Tashman, Fotios Petropoulos (Eds.). International Symposium on Forecasting (ISF) 2018, Boulder (CO), USA, June 16-20, 2018. International Institute of Forecasters PDF \| BibTeX \| RIS \| URL
Harald Schmidbauer, Angi Rösch and Fabian Stieler. 2018. The 2016 US presidential election and media on Instagram: who was in the lead?. Computers in Human Behavior 81, 148-160. DOI: 10.1016/j.chb.2017.11.021 PDF \| BibTeX \| RIS \| DOI
2017
Harald Schmidbauer, Angi Rösch and Fabian Stieler. 2017. Patterns of interest in industrial brands: media uploads to Instagram. In 23rd IIF Workshop on Predictive Analytics and Forecasting (IIF 2017) - Research and Applications, Munich, Germany, September 14-15, 2017. International Institute of Forecasters BibTeX \| RIS