Approximation bounds for random neural networks and reservoir systems

DOI10.1214/22-aap1806arXiv2002.05933OpenAlexW3006049408MaRDI QIDQ6103961

Juan-Pablo Ortega, Lyudmila Grigoryeva, Lukas Gonon

Publication date: 5 June 2023

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2002.05933

zbMATH Keywords

neural networksapproximation errorreservoir computingecho state networksrandom function approximation

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computational methods for problems pertaining to probability theory (60-08) Random operators and equations (aspects of stochastic analysis) (60H25) Stochastic learning and adaptive control (93E35) Approximation by other special function classes (41A30)

Related Items (3)

Transport in reservoir computing ⋮ Convergence rates for shallow neural networks learned by gradient descent ⋮ The Gaussian kernel on the circle and spaces that admit isometric embeddings of the circle

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Probability in Banach spaces. Isoperimetry and processes
• Approximating nonlinear fading-memory operators using neural network models
• On the near optimality of the stochastic approximation of smooth functions by neural networks
• Embedding and approximation theorems for echo state networks
• Echo state networks are universal
• Multidimensional Stochastic Processes as Rough Paths
• Universal approximation bounds for superpositions of a sigmoidal function
• Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With <inline-formula> <tex-math notation="LaTeX">$\ell^1$ </tex-math> </inline-formula> and <inline-formula> <tex-math notation="LaTeX">$\ell^0$ </tex-math> </inline-formula> Controls
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• The identification of nonlinear discrete-time fading-memory systems using neural network models
• Fading memory echo state networks are universal

This page was built for publication: Approximation bounds for random neural networks and reservoir systems