2000 character limit reached
A Predictive Coding Account for Chaotic Itinerancy (2106.08937v1)
Published 16 Jun 2021 in cs.NE, cs.LG, and nlin.CD
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.