Attractor-merging Crises and Intermittency in Reservoir Computing

Tempei Kabayama, Motomasa Komuro, Yasuo Kuniyoshi, Kazuyuki Aihara, Kohei Nakajima
4/17/2025
nlin.CDcs.LGcs.NE

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Seeing double with a multifunctional reservoir computer

84% match2023

Confabulation dynamics in a reservoir computer: Filling in the gaps with untrained attractors

83% match2025

Exploring the origins of switching dynamics in a multifunctional reservoir computer

82% match2024

On the dimension of pullback attractors in recurrent neural networks

81% match2025

Reservoir Computing Generalized

81% match2024

Learning Reservoir Dynamics with Temporal Self-Modulation

81% match2023

Cite this paper

@article{kabayama2025attractormerging,
  title  = {Attractor-merging Crises and Intermittency in Reservoir Computing},
  author = {Tempei Kabayama and Motomasa Komuro and Yasuo Kuniyoshi and Kazuyuki Aihara and Kohei Nakajima},
  year   = {2025},
  eprint = {2504.12695},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.12695v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.12695.svg)](https://codeofpaper.com/paper/2504.12695)

Discussion