# Attractor-merging Crises and Intermittency in Reservoir Computing

arXiv: https://arxiv.org/abs/2504.12695 · HTML: https://mlsanity.com/paper/2504.12695/

## 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 (most cited first, 11 of 11)

- [Physical reservoir computing -- An introductory perspective](https://mlsanity.com/paper/2005.00992/) (2020)
- [Machine learning prediction of critical transition and system collapse](https://mlsanity.com/paper/2012.01545/) (2020)
- [Multifunctionality in a Reservoir Computer](https://mlsanity.com/paper/2008.06348/) (2020)
- [Designing spontaneous behavioral switching via chaotic itinerancy](https://mlsanity.com/paper/2002.08332/) (2020)
- [Seeing double with a multifunctional reservoir computer](https://mlsanity.com/paper/2305.05799/) (2023)
- [Finite-time Lyapunov exponents of deep neural networks](https://mlsanity.com/paper/2306.12548/) (2023)
- [Controlling chaotic itinerancy in laser dynamics for reinforcement learning](https://mlsanity.com/paper/2205.05987/) (2022)
- [Embedding bifurcations into pneumatic artificial muscle](https://mlsanity.com/paper/2305.03994/) (2023)
- [Optimal short-term memory before the edge of chaos in driven random recurrent networks](https://mlsanity.com/paper/1912.11213/) (2019)
- [Exploring the origins of switching dynamics in a multifunctional reservoir computer](https://mlsanity.com/paper/2408.15400/) (2024)
- [Designing Chaotic Attractors: A Semi-supervised Approach](https://mlsanity.com/paper/2407.09545/) (2024)

## 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.