The specialization is driven by the research group Digital Signal Processing and Image Analysis. Projects in signal processing are also possible. Some recent master projects:
-
Invertible and Pseudo-Invertible Encoders: An Approach to Inverse Problems with Neural Networks by Marius Aasan. This thesis motivate the theory of inverse problems via integral equations and spectral theory and discuss the connection of statistical learning theory to neural networks with special focus on encoder-decoder models.
-
Introducing an Efficient Approach for Expressing Uncertainty in Deep Learning with Bayesian Neural Networks by Edward Fabian Bull. This thesis introduce a new numerical method for Monte Carlo simulation applicable for Bayesian deepl learning.