Attractor-merging Crises and Intermittency in Reservoir Computing

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.

@article{kabayama2025_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 }
}