Next-generation reservoir computing for dynamical inference

DOI10.1063/5.0302319MaRDI QIDQ7236941zbMATH OpenFDO

Authors Rok Cestnik, Erik Andreas Martens

Publication date 29 April 2026

Published in Chaos (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1063/5.0302319

Mathematics Subject Classification ID

Dynamical systems and ergodic theory (37-XX) Ordinary differential equations (34-XX)

Cites work

• An equation for continuous chaos
• Confabulation dynamics in a reservoir computer: filling in the gaps with untrained attractors
• Deterministic Nonperiodic Flow
• Echo state networks are universal
• Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks
• Hamiltonian Systems and Transformation in Hilbert Space
• How more data can hurt: instability and regularization in next-generation reservoir computing
• Inferring the dynamics of oscillatory systems using recurrent neural networks
• Limits of learning dynamical systems
• Memory in linear recurrent neural networks in continuous time
• Modern Koopman theory for dynamical systems
• On the theory of the Brownian motion.
• Phase-amplitude descriptions of neural oscillator models
• Re-visiting the echo state property
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Recurrent kernel machines: computing with infinite echo state networks
• Reservoir Computing
• Reservoir computing approaches to recurrent neural network training
• Spectral properties of dynamical systems, model reduction and decompositions
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

This page was built for publication: Next-generation reservoir computing for dynamical inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7236941)