2 papers
math.DS2020
Two methods to approximate the Koopman operator with a reservoir computer
Marvyn Gulina, Alexandre Mauroy
The Koopman operator provides a powerful framework for data-driven analysis of dynamical systems. In the last few years, a wealth of numerical methods providing finite-dimensional…
cs.NE2018
Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography
Piotr Antonik, Marvyn Gulina, Jaël Pauwels +1
Using the machine learning approach known as reservoir computing, it is possible to train one dynamical system to emulate another. We show that such trained reservoir computers rep…