Abstract:Machine learning has become a fundamental approach for modeling, prediction, and control, enabling systems to learn from data and perform complex tasks. Reservoir computing is a machine learning tool that leverages high-dimensional dynamical systems to efficiently process temporal data for prediction and observation tasks. Traditionally, the connectivity of the network that underlies a reservoir computer (RC) is generated randomly, lacking a principled design. Here, we focus on optimizing the connectivity of a linear RC to improve its performance and interpretability, which we achieve by decoupling the RC dynamics into a number of independent modes. We then proceed to optimize each one of these modes to perform a given task, which corresponds to selecting an optimal RC connectivity in terms of a given set of eigenvalues of the RC adjacency matrix. Simulations on networks of varying sizes show that the optimized RC significantly outperforms randomly constructed reservoirs in both training and testing phases and often surpasses nonlinear reservoirs of comparable size. This approach provides both practical performance advantages and theoretical guidelines for designing efficient, task-specific, and analytically transparent RC architectures.
| Subjects: | Systems and Control (eess.SY); Machine Learning (cs.LG); Chaotic Dynamics (nlin.CD) |
| Cite as: | arXiv:2509.23391 [eess.SY] |
| (or arXiv:2509.23391v3 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2509.23391 arXiv-issued DOI via DataCite |
From: Sahand Tangerami [view email]
[v1]
Sat, 27 Sep 2025 16:24:53 UTC (718 KB)
[v2]
Thu, 18 Dec 2025 01:50:52 UTC (2,232 KB)
[v3]
Thu, 16 Apr 2026 01:07:30 UTC (1,745 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。