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

DOI10.1162/neco.1994.6.6.1233zbMath0822.68096OpenAlexW1977294554MaRDI QIDQ4323349

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

sigmoid functionheaviside functionthree-layered feedforward neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

Activation Functions Defined on Higher-Dimensional Spaces for Approximation on Compact Sets with and without Scaling ⋮ Nonlinearity creates linear independence ⋮ Approximation of functions and their derivatives: A neural network implementation with applications

Cites Work

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

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