Constructive approximation by neural networks with positive integer weights

DOI10.11568/KJM.2015.23.3.327MaRDI QIDQ5217025zbMATH OpenOpenAlexFDO

Authors Bum Il Hong, Nahmwoo Hahm

Publication date 21 February 2020

Published in Korean Journal of Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.11568/kjm.2015.23.3.327

zbMATH Keywords

neural networkpositive integer weightsigmoidal function

Mathematics Subject Classification ID

Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Constructive approximation by Gaussian neural networks
• Approximation by neural networks with a restricted set of weights
• The construction and approximation of the neural network with two weights
• Approximation by neural networks with weights varying on a finite set of directions
• An approximation by neural networks with a fixed weight

Cites work

• Approximation by Ridge functions and neural networks with one hidden layer
• Approximation of functions of finite variation by superpositions of a sigmoidal function.
• Constructive approximation by Gaussian neural networks
• Degree of approximation by periodic neural networks
• scientific article; zbMATH DE number 495819 (Why is no real title available?)
• On sigmoidal functions
• The dynamic universality of sigmoidal neural networks

Cited in

(3)

• An approximation by neural networks with a fixed weight
• The construction and approximation of the neural network with two weights
• Constructive approximation by Gaussian neural networks

This page was built for publication: Constructive approximation by neural networks with positive integer weights

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5217025)