activity
20212026
most citedDynamical system analysis of a data-driven model constructed by reservoir computing

24 citations · 27 across the 5 of their papers we have counts for

collaborators

6 papers

nlin.CD2026

Geometric structure of ideal data-driven dynamical model using RfR method

Natsuki Tsutsumi, Kengo Nakai, Yoshitaka Saiki

The Gaussian radial function-based Regression (RfR) method is a data-driven modeling approach that utilizes physically understandable variables from scalar time series, constructed…

nlin.CD2025

On the attractor in a high-dimensional neural network dynamics of reservoir computing: Lyapunov analysis viewpoint

Miki U. Kobayashi, Kengo Nakai, Yoshitaka Saiki +1

Recent theoretical developments of reservoir computing have clarified a sufficient condition about which reservoir computing can capture the dynamics of a target system, enabling t…

nlin.CD2024

Data-driven ODE modeling of the high-frequency complex dynamics via a low-frequency dynamics model

Natsuki Tsutsumi, Kengo Nakai, Yoshitaka Saiki

In our previous paper [N. Tsutsumi, K. Nakai and Y. Saiki, Chaos 32, 091101 (2022)], we proposed a method for constructing a system of differential equations of chaotic behavior fr…

math.DS2023

Constructing low-dimensional ordinary differential equations from chaotic time series of high/infinite-dimensional systems using radial function-based regression

Natsuki Tsutsumi, Kengo Nakai, Yoshitaka Saiki

In our previous study (N. Tsutsumi, K. Nakai and Y. Saiki (2022)) we proposed a method of constructing a system of differential equations of chaotic behavior only from observable d…

math.DS2022★ 3 cited

Constructing differential equations using only a scalar time-series about continuous time chaotic dynamics

Natsuki Tsutsumi, Kengo Nakai, Yoshitaka Saiki

We propose a simple method of constructing a system of differential equations of chaotic behavior based on the regression only from a scalar observable time-series data. The estima…

math.DS2021★ 24 cited

Dynamical system analysis of a data-driven model constructed by reservoir computing

Miki U Kobayashi, Kengo Nakai, Yoshitaka Saiki +1

This study evaluates data-driven models from a dynamical system perspective, such as unstable fixed points, periodic orbits, chaotic saddle, Lyapunov exponents, manifold structures…