Echo state networks are universal

DOI10.1016/j.neunet.2018.08.025zbMath1434.68409arXiv1806.00797OpenAlexW2963003308WikidataQ57492840 ScholiaQ57492840MaRDI QIDQ2182904

Juan-Pablo Ortega, Lyudmila Grigoryeva

Publication date: 26 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.00797

zbMATH Keywords

universalitymachine learninguniform system approximationecho state networks (ESN)fading memory filtersreservoir computing (RC)

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (32)

The echo index and multistability in input-driven recurrent neural networks ⋮ Unnamed Item ⋮ Modeling chaotic systems: dynamical equations vs machine learning approach ⋮ Neural kernels for recursive support vector regression as a model for episodic memory ⋮ Unnamed Item ⋮ Predicting turbulent dynamics with the convolutional autoencoder echo state network ⋮ A framework for machine learning of model error in dynamical systems ⋮ Fading memory echo state networks are universal ⋮ Robust optimization and validation of echo state networks for learning chaotic dynamics ⋮ Real-time thermoacoustic data assimilation ⋮ Transport in reservoir computing ⋮ Approximation bounds for random neural networks and reservoir systems ⋮ Generalised synchronisations, embeddings, and approximations for continuous time reservoir computers ⋮ Inferring unknown unknowns: regularized bias-aware ensemble Kalman filter ⋮ Unnamed Item ⋮ Stability analysis of chaotic systems from data ⋮ Learning strange attractors with reservoir systems ⋮ Designing universal causal deep learning models: The geometric (Hyper)transformer ⋮ Data-driven reconstruction of nonlinear dynamics from sparse observation ⋮ Embedding and approximation theorems for echo state networks ⋮ Echo state network-based online optimal control for discrete-time nonlinear systems ⋮ Stability and memory-loss go hand-in-hand: three results in dynamics and computation ⋮ Unnamed Item ⋮ Predicting critical transitions in multiscale dynamical systems using reservoir computing ⋮ Breaking symmetries of the reservoir equations in echo state networks ⋮ Parameter extraction with reservoir computing: Nonlinear time series analysis and application to industrial maintenance ⋮ Dimension reduction in recurrent networks by canonicalization ⋮ Unnamed Item ⋮ Symmetry kills the square in a multifunctional reservoir computer ⋮ Learning nonlinear input-output maps with dissipative quantum systems ⋮ Embedding information onto a dynamical system ⋮ Memory and forecasting capacities of nonlinear recurrent networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reservoir computing approaches to recurrent neural network training
• Expressive power of first-order recurrent neural networks determined by their attractor dynamics
• A fixed-point farrago
• Structure theorems for nonlinear systems
• Approximating nonlinear fading-memory operators using neural network models
• Multilayer feedforward networks are universal approximators
• Notes on fading-memory conditions
• The dynamic universality of sigmoidal neural networks
• Re-visiting the echo state property
• An experimental unification of reservoir computing methods
• A local echo state property through the largest Lyapunov exponent
• On the mathematical foundations of learning
• Learning Theory
• Fading memory and the problem of approximating nonlinear operators with Volterra series
• Closedness of sum spaces and the generalized Schrödinger problem
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Echo State Property Linked to an Input: Exploring a Fundamental Characteristic of Recurrent Neural Networks
• A Representation Theorem for Continuous Functions of Several Variables
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Echo state networks are universal