Dennis Adamek

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.