Stabilizing chaotic dynamical system reproduction in reservoir computing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914323275710464 |
|---|---|
| author | Oishi, Satoshi Yamashita, Hiroshi Suzuki, Hideyuki Shirasaka, Sho |
| author_facet | Oishi, Satoshi Yamashita, Hiroshi Suzuki, Hideyuki Shirasaka, Sho |
| contents | Reservoir Computing (RC), a type of recurrent random neural network, is a powerful framework for modeling complex and chaotic dynamics. However, its autonomous (closed-loop) operation is often plagued by inherent instability. Moreover, performance is highly sensitive to the reservoir's random initialization, leading to vulnerability to noise and/or behaviour that bears no resemblance whatsoever to the target dynamical system. Here we identify a primary cause of this unreliability: the emergence of excessive, spurious unstable or neutral modes in the closed-loop dynamics. We introduce a simple deterministic input layer design principle that directly addresses this vulnerability by structurally suppressing the emergence of these spurious modes a priori (before training). Our approach dramatically improves robustness to both initialization sensitivity and internal noise, doubling the prediction horizon. Furthermore, we demonstrate on chaotic dynamical systems that this design enables robust estimation of the full Lyapunov spectrum (100\% success rate across 50 seeds), signifying that the autonomous RC faithfully emulates the essential properties of the target dynamical system. This work provides a systematic explanation for a common RC failure mode and offers a concrete design guideline, advancing RCs from heuristic trial-and-error tuning toward a reliable tool for modeling complex systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11069 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stabilizing chaotic dynamical system reproduction in reservoir computing Oishi, Satoshi Yamashita, Hiroshi Suzuki, Hideyuki Shirasaka, Sho Chaotic Dynamics Reservoir Computing (RC), a type of recurrent random neural network, is a powerful framework for modeling complex and chaotic dynamics. However, its autonomous (closed-loop) operation is often plagued by inherent instability. Moreover, performance is highly sensitive to the reservoir's random initialization, leading to vulnerability to noise and/or behaviour that bears no resemblance whatsoever to the target dynamical system. Here we identify a primary cause of this unreliability: the emergence of excessive, spurious unstable or neutral modes in the closed-loop dynamics. We introduce a simple deterministic input layer design principle that directly addresses this vulnerability by structurally suppressing the emergence of these spurious modes a priori (before training). Our approach dramatically improves robustness to both initialization sensitivity and internal noise, doubling the prediction horizon. Furthermore, we demonstrate on chaotic dynamical systems that this design enables robust estimation of the full Lyapunov spectrum (100\% success rate across 50 seeds), signifying that the autonomous RC faithfully emulates the essential properties of the target dynamical system. This work provides a systematic explanation for a common RC failure mode and offers a concrete design guideline, advancing RCs from heuristic trial-and-error tuning toward a reliable tool for modeling complex systems. |
| title | Stabilizing chaotic dynamical system reproduction in reservoir computing |
| topic | Chaotic Dynamics |
| url | https://arxiv.org/abs/2602.11069 |