How more data can hurt: instability and regularization in next-generation reservoir computing (Q6922752)

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

How more data can hurt: instability and regularization in next-generation reservoir computing

scientific article; zbMATH DE number 8100284

Language	Label	Description	Also known as
default for all languages	No label defined
English	How more data can hurt: instability and regularization in next-generation reservoir computing	scientific article; zbMATH DE number 8100284

Statements

instance of

scholarly article

0 references

title

How more data can hurt: instability and regularization in next-generation reservoir computing (English)

0 references

author

Yuanzhao Zhang

0 references

Edmilson Roque dos Santos

0 references

0 references

0 references

0 references

30 September 2025

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

A proposal on machine learning via dynamical systems

0 references

A framework for machine learning of model error in dynamical systems

0 references

Discovering governing equations from data by sparse identification of nonlinear dynamical systems

0 references

Hybridizing traditional and next-generation reservoir computing to accurately and efficiently forecast dynamical systems

0 references

Reconciling modern machine-learning practice and the classical bias-variance trade-off

0 references

Deep double descent: where bigger models and more data hurt*

0 references

On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD

0 references

Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations

0 references

Nonlinear system identification. NARMAX methods in the time, frequency, and spatio-temporal domains

0 references

Learning unseen coexisting attractors

0 references

Controlling chaotic maps using next-generation reservoir computing

0 references

The size of the sync basin

0 references

The size of the sync basin revisited

0 references

Q3805940

0 references

Numerical Methods for Computing Angles Between Linear Subspaces

0 references

Recovering sparse networks: basis adaptation and stability under extensions

0 references

Q5689624

0 references

Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

0 references

Echo state networks are universal

0 references

Do reservoir computers work best at the edge of chaos?

0 references

Using machine learning to predict statistical properties of non-stationary dynamical processes: System climate,regime transitions, and the effect of stochasticity

0 references

Using data assimilation to train a hybrid forecast system that combines machine-learning and knowledge-based components

0 references

Model-free inference of unseen attractors: reconstructing phase space features from a single noisy trajectory using Reservoir computing

0 references

Multifunctionality in a reservoir computer

0 references

Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations

0 references

Approximation bounds for random neural networks and reservoir systems

0 references

Reservoir computing as digital twins for nonlinear dynamical systems

0 references

Q5214289

0 references

Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation

0 references

Two models of double descent for weak features

0 references

The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve

0 references

Identifiers

DOI

10.1063/5.0262977

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi How more data can hurt: instability and regularization in next-generation reservoir computing