After obtaining his MSc in Computer Engineering, Manuel Wöllhaf started working as a doctoral student in Prof. Hellwich’s lab. His research is focused on the perceptive systems of artificial agents. Visual sensors in biological and synthetic intelligent systems provide high-dimensional data with complex structural relationships between their elements. Especially if the input has a time component, as in the visual system of an acting agent, the data stream has to be compressed to allow for efficient decision-making. Therefore, Manuel aims to identify and integrate priors in self and unsupervised learning frameworks that help to reduce redundancy in the visual signal.