English

A Predictive Coding Account for Chaotic Itinerancy

Neural and Evolutionary Computing 2021-06-17 v1 Machine Learning Chaotic Dynamics

Abstract

As a phenomenon in dynamical systems allowing autonomous switching between stable behaviors, chaotic itinerancy has gained interest in neurorobotics research. In this study, we draw a connection between this phenomenon and the predictive coding theory by showing how a recurrent neural network implementing predictive coding can generate neural trajectories similar to chaotic itinerancy in the presence of input noise. We propose two scenarios generating random and past-independent attractor switching trajectories using our model.

Keywords

Cite

@article{arxiv.2106.08937,
  title  = {A Predictive Coding Account for Chaotic Itinerancy},
  author = {Louis Annabi and Alexandre Pitti and Mathias Quoy},
  journal= {arXiv preprint arXiv:2106.08937},
  year   = {2021}
}
R2 v1 2026-06-24T03:16:41.641Z