Attractor-merging Crises and Intermittency in Reservoir Computing
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 53 references that are in the map. First posted on arXiv 17 Apr 2025.
Builds on
11 of 53 references.
References · 11
- 2020Physical reservoir computing -- An introductory perspectivecited by 58
- 2020Machine learning prediction of critical transition and system collapsecited by 54
- 2020Multifunctionality in a Reservoir Computercited by 21
- 2020Designing spontaneous behavioral switching via chaotic itinerancycited by 13
- 2023Seeing double with a multifunctional reservoir computercited by 12
- 2023Finite-time Lyapunov exponents of deep neural networkscited by 12
- 2022Controlling chaotic itinerancy in laser dynamics for reinforcement learningcited by 7
- 2023Embedding bifurcations into pneumatic artificial musclecited by 7
- 2019Optimal short-term memory before the edge of chaos in driven random recurrent networkscited by 6
- 2024Exploring the origins of switching dynamics in a multifunctional reservoir computercited by 4
- 2024Designing Chaotic Attractors: A Semi-supervised Approachcited by 3
Built on by
Not cited yet.