Jul 2026· SIAM Journal on Applied Dynamical Systems· Vol 25, pp. 1834-1867· 0 citations· 18 references
Computer Science
TL;DR
It is proved that, under certain assumptions, a reservoir that has learned topologically semiconjugate in a weak sense or topologically conjugate to [Formula] becomes topologically semiconjugate in a weak sense or topologically conjugate to [Formula]: see text.
Abstract
Abstract.
Reservoir computing (RC) is a machine learning framework based on recurrent neural networks, which can naturally be viewed as dynamical systems. We focus on the problem of learning a time series generated by an unknown dynamical system [Formula: see text]. As suggested by several numerical studies, once the reservoir has learned [Formula: see text], it appears to reproduce the dynamics of [Formula: see text]; however, the underlying mechanism behind this behavior has not yet been fully clarified. In this study, we prove that, under certain assumptions, a reservoir that has learned [Formula: see text] becomes topologically semiconjugate in a weak sense or topologically conjugate to [Formula: see text]. This theorem and its proof shed new light on the mathematical foundations of RC.
Reservoir computing (RC) is a machine learning technique for data-driven modeling of dynamics for forecasting and control, primarily studied in computer science and physics literature with promising applications in neural network learning, physical computing, and neuroscience. Why reservoirs learn and how to choose goo...
A. Bizyaeva, Fernando Castaños, Jaime A. Moreno· 1 citation
In this paper, we propose a new model: infinite dimensional Lotka–Volterra–Hopfield (LVH) system, which is a combination of two celebrated models—the multispecies Lotka–Volterra system and the Hopfield model. We show that the LVH model enjoys a remarkable property: it serves as a dynamical analogue of universal Turing...
Karina Kurtova, S. Vakulenko, Dmitry Grigoryev· Journal of Physics A: Mathem...· 0 citations
The paper studies learning in reservoir computing systems through the lens of the internal model principle. The key idea is to model training signals as outputs of an exogenous signal generator, thus connecting reservoir computing to output regulation, observer theory, and frequency-domain interpolation. For linear sig...
Data-driven machine learning has established a robust foundation for reconstructing nonlinear dynamical systems from observations, primarily for the purposes of forecasting and control. However, most existing efforts focus on recovering specific observed dynamics rather than the generative synthesis of new ones. Inspir...
The Lyapunov spectrum of a nonlinear recurrent neural network with random asymmetric couplings is calculated in the limit $N\to\infty$. The calculation is based on a finite-$N$ identity that expresses the cumulative distribution of Lyapunov exponents as a response function of the tangent-space dynamics, with the tangen...
Autoregressive models are trained to predict a system's behavior one step at a time, and recursive generation allows the learned dynamics to unfold over long horizons. To what extent can such dynamics learned from local observations recover broader organization of an underlying system that was only partially observed d...
Yi-Lun Liu, Yi Zhang, Gan-Yu Wu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
