Fading memory echo state networks are universal

DOI10.1016/j.neunet.2021.01.025zbMath1521.68119arXiv2010.12047OpenAlexW3128485317MaRDI QIDQ6078702

Lukas Gonon, Juan-Pablo Ortega

Publication date: 28 September 2023

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

Full work available at URL: https://arxiv.org/abs/2010.12047

zbMATH Keywords

universalitymachine learningecho state networkreservoir computingecho state propertyfading memory property

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (10)

Robust optimization and validation of echo state networks for learning chaotic dynamics ⋮ Reservoir computing with error correction: long-term behaviors of stochastic dynamical systems ⋮ Transport in reservoir computing ⋮ Approximation bounds for random neural networks and reservoir systems ⋮ Generalised synchronisations, embeddings, and approximations for continuous time reservoir computers ⋮ Learning Theory for Dynamical Systems ⋮ Calibration of spatiotemporal forecasts from citizen science urban air pollution data with sparse recurrent neural networks ⋮ Learning strange attractors with reservoir systems ⋮ Designing universal causal deep learning models: The geometric (Hyper)transformer ⋮ Dimension reduction in recurrent networks by canonicalization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reservoir computing approaches to recurrent neural network training
• Approximating nonlinear fading-memory operators using neural network models
• Multilayer feedforward networks are universal approximators
• Embedding and approximation theorems for echo state networks
• Echo state networks are universal
• Stochastic nonlinear time series forecasting using time-delay reservoir computers: performance and universality
• Fading memory and the problem of approximating nonlinear operators with Volterra series
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Fading memory echo state networks are universal