Łukasz Kuśmierz

This paper studies RNNs with heavy-tailed distributions and finds a slow transition to chaos with tradeoffs in dynamical robustness and dimensionality.

The paper shows that chaotic dynamics in recurrent neural networks separate learning regimes and correlate with a consciousness measure, suggesting a link between critical dynamics, learning, and consciousness.

This paper models decision-making under uncertainty using Bayesian anchoring to explain the fourfold pattern of risk attitudes and related effects observed in experiments.