SOURCE-LINKED INTELLIGENCE

Learning-Induced Dynamical Transition in Recurrent Neural Networks

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Learning in recurrent neural networks can fundamentally reshape their underlying dynamics, transforming initially chaotic activity into stable task-dependent behavior. We develop a non-equilibrium dynamical mean-field theory(DMFT) to describe this transition during learning. We show that a slow feedback-driven learning process generates an evolving effective feedback strength that drives the network through a transition from chaotic to stable dynamics defined by a bifurcation of the DMFT solution. By deriving the two-time correlation function throughout learning, we identify a critical feedbac

Read original source ↗ Open in workspace

recordType

paper

region

Global