Attractor-merging Crises and Intermittency in Reservoir Computing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kabayama, Tempei, Komuro, Motomasa, Kuniyoshi, Yasuo, Aihara, Kazuyuki, Nakajima, Kohei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916955896676352
author Kabayama, Tempei
Komuro, Motomasa
Kuniyoshi, Yasuo
Aihara, Kazuyuki
Nakajima, Kohei
author_facet Kabayama, Tempei
Komuro, Motomasa
Kuniyoshi, Yasuo
Aihara, Kazuyuki
Nakajima, Kohei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12695
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Attractor-merging Crises and Intermittency in Reservoir Computing
Kabayama, Tempei
Komuro, Motomasa
Kuniyoshi, Yasuo
Aihara, Kazuyuki
Nakajima, Kohei
Chaotic Dynamics
Machine Learning
Neural and Evolutionary Computing
Dynamical Systems
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.
title Attractor-merging Crises and Intermittency in Reservoir Computing
topic Chaotic Dynamics
Machine Learning
Neural and Evolutionary Computing
Dynamical Systems
url https://arxiv.org/abs/2504.12695