Approximation by neural networks with a generalized sigmoidal function

zbMATH Open1408.41014MaRDI QIDQ4619783FDOQ4619783

Authors: Bum Il Hong, N. W. Hahm 

Publication date: 7 February 2019

Recommendations

• Approximation by series of sigmoidal functions with applications to neural networks
• An approximation by neural networks with a fixed weight
• Approximation by neural networks with sigmoidal functions
• scientific article; zbMATH DE number 740111
• Univariate sigmoidal neural newtwork approximation

zbMATH Keywords

Heaviside functionneural networksgeneralized sigmoidal function

Mathematics Subject Classification ID

Approximation by other special function classes (41A30) Algorithms for approximation of functions (65D15) Approximation by arbitrary linear expressions (41A45)

Cited In (16)

• Approximating smooth functions by deep neural networks with sigmoid activation function
• An approximation problems on \(L_2(\mathbb R)\) by wavelet neural network
• The exponential learning equation as a function of successful trials results in sigmoid performance
• An approximation by neural networks with a fixed weight
• The dynamic universality of sigmoidal neural networks
• An analysis on neural dynamics with saturated sigmoidal functions
• Approximation problems in sigma-pi neural networks
• Multivariate sigmoidal neural network approximation
• Title not available (Why is that?)
• An investigation of approximate solutions for second order ordinary differential equations using sigmoid-weighted neural networks
• Title not available (Why is that?)
• Sigmoidal approximations of Heaviside functions in neural lattice models
• Generalizing the sigmoid function using continuous-valued logic
• Approximation with neural networks activated by ramp sigmoids
• Sigmoid generators for neural computing using piecewise approximations
• Title not available (Why is that?)

This page was built for publication: Approximation by neural networks with a generalized sigmoidal function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4619783)