Lab – Machine Learning and Neural Networks
The research group focuses on understanding the mechanisms by which neural networks can solve problems that cannot be solved by superficial pattern recognition, and which allow them to extrapolate into combinatorially extensive state spaces associated with language and reasoning. Most of our research time is spent designing hypotheses for these mechanisms and testing them on an empirical basis. Several members of our group also translate these findings into methods that make neural networks more robust and computationally efficient.
Updated: 19. 03. 2025
