Reducing network size and improving prediction stability of reservoir computing

DOI10.1063/5.0006869zbMath1440.37076arXiv2003.03178OpenAlexW3100551378WikidataQ96949365 ScholiaQ96949365MaRDI QIDQ5119469

Joschka Herteux, Alexander Haluszczynski, Jonas Aumeier, Christoph Räth

Publication date: 4 September 2020

Published in: Chaos: An Interdisciplinary Journal of Nonlinear Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.03178

Mathematics Subject Classification ID

Simulation of dynamical systems (37M05)

Related Items (2)

Seeking optimal parameters for achieving a lightweight reservoir computing: a computational endeavor ⋮ Breaking symmetries of the reservoir equations in echo state networks

Cites Work

• Unnamed Item
• Unnamed Item
• Reservoir computing approaches to recurrent neural network training
• Determining Lyapunov exponents from a time series
• Measuring the strangeness of strange attractors
• Chaos in fractional-order autonomous nonlinear systems.
• A practical method for calculating largest Lyapunov exponents from small data sets
• An experimental unification of reservoir computing methods
• An equation for continuous chaos
• The double scroll
• Chaos in models of double convection
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• YET ANOTHER CHAOTIC ATTRACTOR
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• Deterministic Nonperiodic Flow
• Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computing
• Creation of a complex butterfly attractor using a novel Lorenz-Type system
• DETERMINISTIC CHAOS SEEN IN TERMS OF FEEDBACK CIRCUITS: ANALYSIS, SYNTHESIS, "LABYRINTH CHAOS"
• Ridge Regression: Biased Estimation for Nonorthogonal Problems

This page was built for publication: Reducing network size and improving prediction stability of reservoir computing