Approximation Capability of Layered Neural Networks with Sigmoid Units on Two Layers

DOI10.1162/NECO.1994.6.6.1233MaRDI QIDQ4323349zbMATH OpenOpenAlexFDO

Authors Yoshifusa Ito

Publication date 16 February 1995

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco.1994.6.6.1233

zbMATH Keywords

heaviside functionsigmoid functionthree-layered feedforward neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 1083116
• Universal approximation bounds for superpositions of a sigmoidal function
• Approximation by superpositions of a sigmoidal function
• On the approximation by neural networks with bounded number of neurons in hidden layers
• scientific article; zbMATH DE number 740111

Cites work

• Approximation by superpositions of a sigmoidal function
• Multilayer feedforward networks are universal approximators

Cited in

(7)

• Nonlinearity creates linear independence
• Approximation of functions and their derivatives: A neural network implementation with applications
• Universal approximation bounds for superpositions of a sigmoidal function
• On the Partitioning Capabilities of Feedforward Neural Networks with Sigmoid Nodes
• Activation Functions Defined on Higher-Dimensional Spaces for Approximation on Compact Sets with and without Scaling
• scientific article; zbMATH DE number 2193402 (Why is no real title available?)
• Approximation by a class of neural network operators on scattered data

This page was built for publication: Approximation Capability of Layered Neural Networks with Sigmoid Units on Two Layers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4323349)