Neural Networks for Functional Approximation and System Identification

DOI10.1162/neco.1997.9.1.143zbMath0872.68153OpenAlexW2129580267WikidataQ46210585 ScholiaQ46210585MaRDI QIDQ3123291

Nahmwoo Hahm, Hrushikesh N. Mhaskar

Publication date: 6 March 1997

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

Full work available at URL: https://doi.org/10.1162/neco.1997.9.1.143

zbMATH Keywords

translation networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (7)

Neural networks in Fréchet spaces ⋮ Approximation of nonlinear functionals using deep ReLU networks ⋮ Local approximation of operators ⋮ Convergence rate of DeepONets for learning operators arising from advection-diffusion equations ⋮ Function evaluation with feedforward neural networks ⋮ A Measurement Fusion Method for Nonlinear System Identification Using a Cooperative Learning Algorithm ⋮ Extension of localised approximation by neural networks

Cites Work

• Multilayer feedforward networks are universal approximators
• Optimal nonlinear approximation
• Degree of approximation by neural and translation networks with a single hidden layer
• Control oriented system identification: a worst-case/deterministic approach in H/sub infinity /
• Universal approximation bounds for superpositions of a sigmoidal function
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Neural Networks for Functional Approximation and System Identification