Saturation classes for MAX-product neural network operators activated by sigmoidal functions

DOI10.1007/s00025-017-0692-6zbMath1376.41014OpenAlexW2614181593MaRDI QIDQ1682591

Gianluca Vinti, Danilo Costarelli

Publication date: 30 November 2017

Published in: Results in Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00025-017-0692-6

zbMATH Keywords

sigmoidal functionsneural networks operatorssaturation resultinverse resultFavard classes

Mathematics Subject Classification ID

Linear operator approximation theory (47A58) Interpolation in approximation theory (41A05) Rate of convergence, degree of approximation (41A25) Approximation by other special function classes (41A30)

Related Items (27)

Approximation theorems for a family of multivariate neural network operators in Orlicz-type spaces ⋮ DENSITY RESULTS BY DEEP NEURAL NETWORK OPERATORS WITH INTEGER WEIGHTS ⋮ Approximation by truncated Lupaş operators of max-product kind ⋮ Voronovskaja type theorems and high-order convergence neural network operators with sigmoidal functions ⋮ Modified neural network operators and their convergence properties with summability methods ⋮ Novel bifurcation results for a delayed fractional-order quaternion-valued neural network ⋮ Nonlinear approximation via compositions ⋮ Quantitative estimates for neural network operators implied by the asymptotic behaviour of the sigmoidal activation functions ⋮ Approximation error for neural network operators by an averaged modulus of smoothness ⋮ Some density results by deep Kantorovich type neural network operators ⋮ Approximation error of single hidden layer neural networks with fixed weights ⋮ Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions ⋮ Superposition, reduction of multivariable problems, and approximation ⋮ Estimates for the neural network operators of the max-product type with continuous and \(p\)-integrable functions ⋮ Approximation results in Orlicz spaces for sequences of Kantorovich MAX-product neural network operators ⋮ Deep Network Approximation Characterized by Number of Neurons ⋮ The max-product generalized sampling operators: convergence and quantitative estimates ⋮ Asymptotic expansion for neural network operators of the Kantorovich type and high order of approximation ⋮ Quantitative estimates involving K-functionals for neural network-type operators ⋮ Approximation by exponential sampling type neural network operators ⋮ Convergence of sampling Kantorovich operators in modular spaces with applications ⋮ Extension of saturation theorems for the sampling Kantorovich operators ⋮ On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks ⋮ Approximate solutions of Volterra integral equations by an interpolation method based on ramp functions ⋮ Approximation by mixed operators of max-product-Choquet type ⋮ Approximation by max-product operators of Kantorovich type ⋮ Connections between the Approximation Orders of Positive Linear Operators and Their Max-Product Counterparts

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation by max-product neural network operators of Kantorovich type
• Solving Volterra integral equations of the second kind by sigmoidal functions approximation
• On the approximation by neural networks with bounded number of neurons in hidden layers
• Saturation and inverse results for the Bernstein max-product operator
• Rate of approximation for multivariate sampling Kantorovich operators on some functions spaces
• Intelligent systems. Approximation by artificial neural networks
• Constructive approximate interpolation by neural networks
• The approximation operators with sigmoidal functions
• Uniform approximation by neural networks
• Approximation by neural networks with a bounded number of nodes at each level
• The universal approximation capabilities of cylindrical approximate identity neural networks
• Neural network operators: constructive interpolation of multivariate functions
• Approximation with neural networks activated by ramp sigmoids
• On the near optimality of the stochastic approximation of smooth functions by neural networks
• Approximation by series of sigmoidal functions with applications to neural networks
• Necessary and sufficient condition for multistability of neural networks evolving on a closed hypercube
• A collocation method for solving nonlinear Volterra integro-differential equations of neutral type by sigmoidal functions
• Approximation by neural networks and learning theory
• Max-product neural network and quasi-interpolation operators activated by sigmoidal functions
• Approximation by Max-Product Type Operators
• Deep vs. shallow networks: An approximation theory perspective
• Approximation Results for a General Class of Kantorovich Type Operators
• Convergence for a family of neural network operators in Orlicz spaces
• Nonlinear integral operators with homogeneous kernels: pointwise approximation theorems
• An Integral Upper Bound for Neural Network Approximation
• Degree of Approximation for Nonlinear Multivariate Sampling Kantorovich Operators on Some Functions Spaces
• Universal approximation bounds for superpositions of a sigmoidal function
• Applications of sampling Kantorovich operators to thermographic images for seismic engineering
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Saturation classes for MAX-product neural network operators activated by sigmoidal functions