On the Structure of Continuous Functions of Several Variables

Cites Work

Cited In (30)

On PDE characterization of smooth hierarchical functions computed by neural networks
A survey on universal approximation and its limits in soft computing techniques.
Controllable processes and the fuzzy controller
On application of Gaussian kernels and Laplace functions combined with Kolmogorov's theorem for approximation of functions of several variables
An improvement in the superposition theorem of Kolmogorov
A universal mapping for Kolmogorov's superposition theorem
Computational aspects of Kolmogorov's superposition theorem
Approximative versions of Kolmogorov's superposition theorem, proved constructively
A survey of solved and unsolved problems on superpositions of functions
A Superposition Theorem for Unbounded Continuous Functions
On the approximation by neural networks with bounded number of neurons in hidden layers
JAX-DIPS: neural bootstrapping of finite discretization methods and application to elliptic problems with discontinuities
Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem
A note on computing with Kolmogorov superpositions without iterations
A selective overview of deep learning
Universal approximation by radial basis function networks of Delsarte translates
On the Structure of Representations of Continuous Functions of Several Variables as Finite Sums of Continuous Functions of One Variable
Solving initial-boundary value problems for systems of partial differential equations using neural networks and optimization techniques
Chebyshev approximation by discrete superposition. Application to neural networks
A hybrid genetic fuzzy neural network algorithm designed for classification problems involving several groups
The Kolmogorov-Arnold representation theorem revisited
Regularising neural networks using flexible multivariate activation function
On uniform monotone approximation of continuous monotone functions with the help of translations and dilations of the Laplace integral
Dimension, superposition of functions and separation of points, in compact metric spaces
A three layer neural network can represent any multivariate function
On a constructive proof of Kolmogorov's superposition theorem
Superposition stetiger Abbildungen
Gaussian functions combined with Kolmogorov's theorem as applied to approximation of functions of several variables
Fundamental properties of pair-wise interactions naturally lead to quarks and quark confinement: a theorem motivated by neural universal approximation results
Some aspects of approximation and interpolation of functions artificial neural networks

This page was built for publication: On the Structure of Continuous Functions of Several Variables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5517850)