Reservoir computing with random and optimized time-shifts

DOI10.1063/5.0068941MaRDI QIDQ6558708zbMATH OpenFDO

Authors Enrico Del Frate, Afroza Shirin, F. Sorrentino

Publication date 21 June 2024

Published in Chaos (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1063/5.0068941

Mathematics Subject Classification ID

Modes of computation (nondeterministic, parallel, interactive, probabilistic, etc.) (68Q10) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87)

Cites work

• Dimension of reservoir computers
• Do reservoir computers work best at the edge of chaos?
• Dynamic mode decomposition of numerical and experimental data
• Fading memory and the problem of approximating nonlinear operators with Volterra series
• scientific article; zbMATH DE number 3810550 (Why is no real title available?)
• scientific article; zbMATH DE number 4048925 (Why is no real title available?)
• On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD
• Path length statistics in reservoir computers
• Photonic delay systems as machine learning implementations
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Simple recurrent networks learn context-free and context-sensitive languages by counting.
• Stability analysis of reservoir computers dynamics via Lyapunov functions
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

Cited in

(3)

• Erratum to: ``Reservoir computing with random and optimized time-shifts
• Time shifts to reduce the size of reservoir computers
• Optimizing the network topology of a linear reservoir computer

This page was built for publication: Reservoir computing with random and optimized time-shifts

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6558708)