Multilayer feedforward neural networks: a canonical form approximation of nonlinearity

DOI10.1080/00207179208934333MaRDI QIDQ4020181zbMATH OpenOpenAlexFDO

Authors Zhenni Wang, Ming. T. Tham, A. Julian Morris

Publication date 16 January 1993

Published in International Journal of Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/00207179208934333

zbMATH Keywords

neural networkblack boxmultilayer feedforward neural networks

Mathematics Subject Classification ID

Canonical structure (93B10) Geometric methods (93B27)

Recommendations

• Multilayer feedforward networks are universal approximators
• Publication:4861615
• scientific article; zbMATH DE number 2193402
• Robustness of representations in multilayer feedforward neural networks
• scientific article; zbMATH DE number 1234090

Cites work

• scientific article; zbMATH DE number 3246460 (Why is no real title available?)
• Approximation by superpositions of a sigmoidal function
• Multilayer feedforward networks are universal approximators
• Real and functional analysis

Cited in

(9)

• Representation of the neural networks by the game method for modelling
• A review of NQR signal processing and analysis techniques
• scientific article; zbMATH DE number 2193402 (Why is no real title available?)
• Neural networks based subgrid scale modeling in large eddy simulations
• Performance comparison of neural network models: backpropagationvs. fuzzy artmap
• scientific article; zbMATH DE number 836441 (Why is no real title available?)
• Multilayer feedforward networks are universal approximators
• Representation and Extrapolation in Multilayer Perceptrons
• Techniques for the mathematical analysis of neural networks

This page was built for publication: Multilayer feedforward neural networks: a canonical form approximation of nonlinearity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4020181)