Leo Schwinn

Leo Schwinn, M. Sc.

Researcher & PhD Candidate

Department Artificial Intelligence in Biomedical Engineering (AIBE)
Lehrstuhl für Informatik 14 (Maschinelles Lernen und Datenanalytik)

Room 01.016
Carl-Thiersch-Straße 2b
91052 Erlangen
Germany

Phone number: +49 9131 85-20296
Email: leo.schwinn@fau.de
Website: https://www.mad.tf.fau.de/person/leo-schwinn/

Academic CV

since 01/2022	Internship Mila – Quebec AI Institute Supervised by Doina Precup
since 09/2019	Researcher and PhD Candidate Machine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
01/2019-03/2019	Scientific Assistant IT Security Infrastructures Lab (CS1), Department of Computer Science, Friedrich-Alexander-Universität (FAU)
10/2017-08/2019	M.Sc. in Medical Engineering, “Medical Image and Data Processing” Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Majors: Pattern Recognition, Machine Learning, Deep Learning Master’s Thesis: “Learning Feature Extraction for End-to-End Speaker Recognition with Deep Neural Networks”
10/2014-10/2017	B.Sc. in Medical Engineering, “Medical Imaging Systems” Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Majors: Pattern Recognition Bachelor’s Thesis: “Unterscheidung von Sprachpathologien durch Sprechererkennungsverfahren”

Research Projects

SHIELD

Teaching

MLTS Excercise

Publications

2021

Bungert L., Raab R., Roith T., Schwinn L., Tenbrinck D.:
CLIP: Cheap Lipschitz Training of Neural Networks
International Conference on Scale Space and Variational Methods in Computer Vision
In: Abderrahim Elmoataz, Jalal Fadili, Yvain Quéau, Julien Rabin, Loïc Simon (ed.): SSVM 2021: Scale Space and Variational Methods in Computer Vision, Cham: 2021
DOI: 10.1007/978-3-030-75549-2_25
URL: https://arxiv.org/abs/2103.12531
BibTeX: Download
Nguyen A., Foerstel S., Kittler T., Kurzyukov A., Schwinn L., Zanca D., Hipp T., Jun SD., Schrapp M., Rothgang E., Eskofier B.:
System Design for a Data-Driven and Explainable Customer Sentiment Monitor Using IoT and Enterprise Data
In: IEEE Access (2021)
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2021.3106791
BibTeX: Download
Schwinn L., Nguyen A., Raab R., Bungert L., Tenbrinck D., Zanca D., Burger M., Eskofier B.:
Identifying untrustworthy predictions in neural networks by geometric gradient analysis
Conference on Uncertainty in Artificial Intelligence (UAI) (Online, 27. July 2021 - 30. July 2021)
URL: https://arxiv.org/abs/2102.12196
BibTeX: Download
Schwinn L., Nguyen A., Raab R., Zanca D., Eskofier B., Tenbrinck D., Burger M.:
Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks
International Joint Conference on Neural Networks (IJCNN) (Online, 18. July 2021 - 22. July 2021)
BibTeX: Download
Schwinn L., Raab R., Nguyen A., Zanca D., Eskofier B.:
Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks
URL: https://arxiv.org/abs/2105.10304
BibTeX: Download

2020

Nguyen A., Chatterjee S., Weinzierl S., Schwinn L., Matzner M., Eskofier B.:
Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring
International Conference on Process Mining (Padua, 4. October 2020 - 9. October 2020)
In: Proceedings of the 1st International Workshop on Leveraging Machine Learning in Process Mining 2020
BibTeX: Download

2019

Schwinn L., Haderlein T., Nöth E., Maier A.:
Impact of Pathologies on Automatic Age Estimation
Fortschritte der Akustik - DAGA 2019 (DAGA 2019 - 45. Jahrestagung für Akustik) (Rostock, 18. March 2019 - 21. March 2019)
In: Deutsche Gesellschaft für Akustik e.V. (ed.): Fortschritte der Akustik - DAGA 2019, Rostock: 2019
URL: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2019/Schwinn19-IOP.pdf
BibTeX: Download

Student Theses

Year	Name	Title
2022	Tim Löhr	AI Trend Detection in Healthcare by applying Topic Clustering and Sentiment Analysis using Podcast Data (Master’s Thesis, Co-Supervision)
2022	Andrey Kurzyukov	Modeling Mixed-Type Time Series Data for Machinery Health Prognostics (Master’s Thesis, Co-Supervision)
2021	Klaus Fischer	Unsupervised Adversarial Representation Learning (Master’s Project)
2021	Kenneth Mayer	Improving Human Gait Analysis by Super-Resolution and Generative Adversarial Networks (Master’s Project, Co-Supervision)
2021	Jonas Utz	Unsupervised Modeling of Visual Attention (Master’s Project, Co-Supervision)
2021	Meike Biendl	Exploring Connections between Visual Attention and Adversarial Robustness (Master’s Thesis)
2021	Pavlo Beylin	Simultaneous Classification and Identification of Adversarial Attacks Through Multi-Task Learning (Master’s Thesis)
2021	Johannes Roider	Modeling Mixed-Type Time Series Data With Neural Networks for Predictive Maintenance (Master’s Thesis, Co-Supervision)
2021	Tassilo Elsberger	Analysis of Artificial Intelligence Trends in German Economics and Politics – A Data-Driven Approach (Master’s Thesis, Co-Supervision)
2021	Miaomiao Li	Adaptive Lipschitz Regularization of Neural Networks through Matrix Decomposition (Master’s Thesis)
2021	Long Do	Artificial Intelligence trend analysis using speech-to-text data from healthcare podcasts (Master’s Thesis, Co-Supervision)
2020	Pavlo Beylin	Development of a Modular Adversarial Attack Framework and Evaluation on the Sampled Nonlocal Gradient Descent Method (Master’s Project)
2020	Osman Demir	group:Anomaly Semantic Segmentation with Learnable Wavelet Filters (Master’s Thesis)
2020	Darko Boshkovski	group:Using speech recognition techniques for the application of online handwriting recognition (Bachelor’s Thesis, Co-Supervision)

Leo Schwinn

Leo Schwinn, M. Sc.

Academic CV Academic CV

Research Projects Research Projects

Teaching Teaching

Publications Publications