2 papers
math.DS2021
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…
physics.comp-ph2018
Machine-learning inference of fluid variables from data using reservoir computing
Kengo Nakai, Yoshitaka Saiki
We infer both microscopic and macroscopic behaviors of a three-dimensional chaotic fluid flow using reservoir computing. In our procedure of the inference, we assume no prior knowl…