Attractor-merging Crises and Intermittency in Reservoir Computing
Chaotic Dynamics
2025-09-19 v1 Machine Learning
Neural and Evolutionary Computing
Dynamical Systems
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.
Cite
@article{arxiv.2504.12695,
title = {Attractor-merging Crises and Intermittency in Reservoir Computing},
author = {Tempei Kabayama and Motomasa Komuro and Yasuo Kuniyoshi and Kazuyuki Aihara and Kohei Nakajima},
journal= {arXiv preprint arXiv:2504.12695},
year = {2025}
}
Comments
20 pages, 15 figures