Members

I'm a PhD candidate at the Department of Mathematics and Statistics and the Machine Learning Group at UiT and work on uncertainty estimation in deep learning for object classification with a focus on subsea mapping applications. The main goal of my PhD project is to develop fast uncertainty estimation methods that can be used in real-time settings, while still producing accurate and reliable estimates. Another topic we want to investigate in this project is how synthetic data can be used to understand and improve uncertainty estimation in deep learning-based classification tasks. I have a B.Sc. and M.Sc. degree in physics from Friedrich-Schiller University, Jena, Germany. Before starting my PhD, I spent several years as a research scientist in the private sector, working with hyperspectral imaging systems and applied data analysis for remote sensing and industry applications. My research interests lie within signal and image processing, machine learning and Bayesian uncertainty estimation.

I hold a Master of Science degree in Data Engineering and Analytics from the Technical University of Munich (TUM). Passionate about leveraging artificial intelligence in the medical domain, I have contributed to numerous AI research projects in healthcare and medicine, gaining extensive experience across various fields. Currently I am doing my PhD at UiT on advance representation learning techniques, with a particular emphasis on developing novel similarity measures and clustering methods. My research explores how relationships, extracted from complex datasets such as spatial omics, can capture intricate dependencies beyond pairwise interactions, offering a richer understanding of medical and biological data. Given the challenges posed by varying structures and labelled samples, my work aims to incorporate underlying semantic relationships through knowledge embeddings and non-Euclidean geometries. By leveraging these advanced techniques, seeking to develop more meaningful similarity measures that enhance the analysis of medical and healthcare data, ultimately contributing to improved predictive modelling and decision-making in clinical and biomedical applications.