Storage and recall of multiple chaotic attractors in minimal reservoir computers
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.07.2026 · 36 (7)
DOI: 10.1063/5.0334052 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 30.07.2026. Verfasst von Francesco Martinuzzi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Max Planck Institute for the Physics of Complex Systems, Dresden, Germany. Die Arbeit nennt 104 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Modern predictive modeling increasingly calls for a single learned dynamical substrate to operate across multiple regimes. From a dynamical systems viewpoint, this capability decomposes into the storage of multiple attractors and the recall of the appropriate attractor in response to contextual cues. In reservoir computing, multi-attractor learning has largely been pursued using large, randomly wired reservoirs, on the assumption that stochastic connectivity is required to generate sufficiently rich internal dynamics. At the same time, recent work shows that minimal deterministic reservoirs can match random designs for single-system chaotic forecasting. In this paper, we examine the conditions under which minimal reservoir topologies can learn multiple chaotic attractors across storage and recall settings. Using a storage and recall protocol, we find that minimal architectures struggle when explicit recall is required. We then introduce an input concatenation training strategy, in which two attractors are embedded into a single enlarged input space, and show that these reservoirs can represent the joint evolution of multiple chaotic attractors. We test all 28 unordered system pairs formed from eight three-dimensional chaotic systems. Across the ten deterministic topologies investigated, we do not observe a robust dependence of multi-attractor performance on reservoir topology: No single topology consistently outperforms the others in either the storage-only or cue-dependent recall settings. Our results indicate that minimal reservoirs can learn multiple attractors when they are presented jointly but struggle to reliably recall a specific attractor from a model trained on multiple systems.
Autor:innen und Institutionen
- Max Planck Institute for the Physics of Complex Systems, Dresden, Germany.
ORCID-Profile: Francesco Martinuzzi, Holger Kantz
Zitieren
APA
Martinuzzi, F., & Kantz, H. (2026). Storage and recall of multiple chaotic attractors in minimal reservoir computers. Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(7). https://doi.org/10.1063/5.0334052
Vancouver
Martinuzzi F, Kantz H. Storage and recall of multiple chaotic attractors in minimal reservoir computers. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2026;36(7). doi:10.1063/5.0334052
BibTeX
@article{Martinuzzi2026,
author = {Martinuzzi, Francesco and Kantz, Holger},
title = {Storage and recall of multiple chaotic attractors in minimal reservoir computers},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2026},
volume = {36},
number = {7},
doi = {10.1063/5.0334052}
}
EUVIMED