Topic: message passing

Join TYREX to incorporate database schemas, constraints and rules into relational graph-neural-network message passing. The project investigates neurosymbolic aggregation and relational routes, creates annotated benchmarks, and evaluates accuracy, robustness, data efficiency and interpretability. The renewable 12-month appointment has a planned start on 1 December 2026 and gross monthly pay of EUR 2,788. Telework may be possible after six months.

The idea that perception in humans relies on some form of probabilistic computations has become very popular over the last decades. It has been extremely difficult however to characterize the extent and the nature of the probabilistic representations and operations that are manipulated by neural populations in the human cortex. Several theoretical works suggest that probabilistic representations are present from low-level sensory areas to high-level areas. According to this view, the neural dynamics implements some forms of probabilistic message passing (i.e. neural sampling, probabilistic pop