Attractor-merging Crises and Intermittency in Reservoir Computing
Tempei Kabayama, Motomasa Komuro, Yasuo Kuniyoshi, Kazuyuki Aihara, Kohei Nakajima
公開日: 2025/4/17
Abstract
Reservoir computing can embed attractors into random neural networks (RNNs), generating a ``mirror'' of a target attractor because of its inherent symmetrical constraints. In these RNNs, we report that an attractor-merging crisis accompanied by intermittency emerges simply by adjusting the global parameter. We further reveal its underlying mechanism through a detailed analysis of the phase-space structure and demonstrate that this bifurcation scenario is intrinsic to a general class of RNNs, independent of training data.