Ghost Mechanism: An Analytical Model of Abrupt Learning in Recurrent Networks (opens in new tab)

Author(s): Fatih Dinc, Ege Cirakman, Bariscan Kurtkaya, Mert Yuksekgonul, Yiqi Jiang, Mark J. Schnitzer, and Hidenori TanakaThis study establishes the ghost mechanism as an underlying mechanism for abrupt learning, whereby the recurrent neural network develops ghost points—transient dynamical bottlenecks—and identifies ways to overcome the training instabilities.[Phys. Rev. X 16, 021058] Published Tue Jun 23, 2026