PHD at the University of Basel, Switzerland
Monika Timea Nagy-Huber, a Swiss national, is a PhD candidate in Computer Science at the University of Basel, specializing in Physics-informed Machine Learning Algorithms under the guidance of Prof. Dr. Volker Roth. She is part of the Biomedical Data Analysis research group. Monika holds a Master of Science in Mathematics from the University of Basel, where she focused on Numerics and Algebra-Geometry-Number Theory. Her master’s thesis explored the Local Discontinuous Galerkin Method for solving the Wave Equation. She also earned her Bachelor of Science in Mathematics from the University of Basel. Monika is passionate about integrating advanced mathematical techniques with cutting-edge computer science applications.
Professional Profiles
Education
09/2019 – Present: PhD in Computer Science, University of Basel ‣ Supervisor: Prof. Dr. Volker Roth ‣ Research group: Biomedical Data Analysis ‣ Specialisation: Physics-informed Machine Learning Algorithms 02/2016 – 02/2019: Master of Science in Mathematics, University of Basel ‣ Areas of specialisation: Numerics (Partial Differential Equations for Wave Equations), Algebra-Geometry-Number Theory (Elliptic Curves) ‣ Master’s thesis: “Das lokale diskontinuierliche Galerkin-Verfahren mit lokalem Zeitschrittverfahren zur Lösung der Wellengleichung” (translated: The Local Discontinuous Galerkin Method with Local Time Stepping Method for solving the Wave Equation), Grade 5.5 ‣ Supervisor: Prof. Dr. Marcus J. Grote 09/2011 – 02/2016: Bachelor of Science in Mathematics, University of Basel
Research Focus
Monika Timea Nagy-Huber’s research primarily focuses on the intersection of advanced computational methods and biomedical applications. Her work involves developing and applying physics-informed machine learning algorithms to solve complex problems, such as partial differential equations, relevant to biomedical data analysis. She has contributed to various projects, including studying the effects of LSD on brain connectivity, learning invariances with input-convex neural networks, and creating mesh-free Eulerian physics-informed neural networks. Her interdisciplinary approach leverages deep learning and computational science to address challenges in neuroscience, exercise science, and environmental monitoring, demonstrating a robust expertise in integrating theoretical mathematics with practical applications.
Publications
- Physics-informed boundary integral networks (PIBI-Nets): A data-driven approach for solving partial differential equations, Publication date: 2024.
- Using Machine Learning–Based Algorithms to Identify and Quantify Exercise Limitations in Clinical Practice: Are We There Yet?, Publication date: 2023.
- The effect of lysergic acid diethylamide (LSD) on whole-brain functional and effective connectivity, Publication date: 2023.
- Learning invariances with generalised input-convex neural networks, Publication date: 2022.
- Mesh-free eulerian physics-informed neural networks, Publication date: 2022.
- Mesh-free Eulerian Physics-Informed Neural Networks, Publication date: 2022.
- Visual Understanding in Semantic Segmentation of Soil Erosion Sites in Swiss Alpine Grasslands, Publication date: 2022.
.