Universal Approximation of Multiple Nonlinear Operators by Neural Networks

DOI10.1162/089976602760407964zbMath1057.68084OpenAlexW2120999070WikidataQ78518422 ScholiaQ78518422MaRDI QIDQ4409376

Andrew Back, Tian-Ping Chen

Publication date: 2002

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

Full work available at URL: https://doi.org/10.1162/089976602760407964

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (7)

The universal approximation capabilities of cylindrical approximate identity neural networks ⋮ Multifidelity deep operator networks for data-driven and physics-informed problems ⋮ A hybrid deep neural operator/finite element method for ice-sheet modeling ⋮ Adaptive Classification of Temporal Signals in Fixed-Weight Recurrent Neural Networks: An Existence Proof ⋮ Convergence rate of DeepONets for learning operators arising from advection-diffusion equations ⋮ The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks ⋮ Toward Best Approximation of Nonlinear Systems: A Case of Models with Memory

Cites Work

• Inductively inferring valid logical models of continuous-state dynamical systems
• Multilayer feedforward networks are universal approximators
• STATE-DEPENDENT MODELS: A GENERAL APPROACH TO NON-LINEAR TIME SERIES ANALYSIS

This page was built for publication: Universal Approximation of Multiple Nonlinear Operators by Neural Networks