Learning-Induced Dynamical Transition in Recurrent Neural Networks
Read the original on arXiv Machine Learning →The paper presents a non-equilibrium dynamical mean-field theory (DMFT) that explains how learning reshapes the dynamics of recurrent neural networks, turning initially chaotic activity into stable, task-dependent behavior. It shows that a slow, feedback-driven learning process gradually increases effective feedback strength, driving the network through a bifurcation that marks the transition from chaotic to stable dynamics. By deriving the two-time correlation function, the authors identify a critical feedback strength and a learning-rate-dependent critical time that separate these regimes, and they demonstrate that the theory accurately predicts the network’s output evolution during training, matching numerical simulations.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.