Room number

IDEG050

Telephone number

• office: +43 316 873 - 4386

Position

Research and Teaching Associates

Email

sophie.steger@tugraz.at

Sophie Steger received her Dipl.-Ing. degree in Electrical Engineering from TU Graz in 2022. Her PhD research focuses on uncertainty estimation in deep learning and probabilistic machine learning. She is interested in developing methods for quantifying and disentangling aleatoric and epistemic uncertainty to improve the reliability and interpretability of machine learning models.

---

Publications

• Conference paper Linke J., Steger S., Steinwender P., Kubin G., Pernkopf F. & Schuppler B. (2025) Uncertainty prediction for prominence classification with chroma features. in 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025. [more info]
• Conference paper Kantz B., Steger S., Staudinger C., Feilmayr C., Wachlmayr J., Haberl A., Schuster S. & Pernkopf F. (2025) Input Uncertainty Attribution by Uncertainty Propagation.. [more info]
• Conference paper Steger S., Knoll C., Klein B., Fröning H. & Pernkopf F. (2024) Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles. in 2nd SPIGM - ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling. [more info]
• Chapter Thurai M., Teschl F., Steger S. & Schönhuber M. (2023) Understanding the role of rain drop shapes and fall velocities in rainfall estimation from polarimetric weather radars. . [more info] [doi]
• Abstract Rohrhofer F., Steger S., Posch S., Gößnitzer C. & Geiger B. (2023) Training gives me PINNs and needles – on the complexity of training physics-informed neural networks.. [more info]
• Abstract Rohrhofer F., Steger S., Posch S., Gößnitzer C. & Geiger B. (2023) Training gives me PINNs and needles – on the complexity of training physics-informed neural networks.. [more info]
• Conference paper Teschl F., Thurai M., Steger S., Schönhuber M. & Teschl R. (2023) An ANN Approach to Determine the Radar Cross Section of Non-Rotationally Symmetric Rain Drops. in 17th European Conference on Antennas and Propagation. [more info] [doi]
• Conference paper Steger S., Geiger B. & Śmieja M. (2022) Semi-supervised clustering via information-theoretic markov chain aggregation. in 37th ACM/SIGAPP Symposium On Applied Computing (pp. 1136-1139). [more info] [doi]
• Abstract Steger S., Rohrhofer F. & Geiger B. (2022) How PINNs cheat: Predicting chaotic motion of a double pendulum.. [more info]