On a constructive proof of Kolmogorov's superposition theorem

DOI10.1007/s00365-009-9054-2zbMath1194.26020OpenAlexW2062368570MaRDI QIDQ843717

Jürgen Braun, Michael Griebel

Publication date: 15 January 2010

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00365-009-9054-2

zbMATH Keywords

Komogorov's superposition theoremsuperposition of functions

Mathematics Subject Classification ID

Representation and superposition of functions (26B40)

Related Items (11)

High-Discrepancy Sequences for High-Dimensional Numerical Integration ⋮ Neural network approximation: three hidden layers are enough ⋮ Some aspects of approximation and interpolation of functions artificial neural networks ⋮ The Kolmogorov-Arnold representation theorem revisited ⋮ A three layer neural network can represent any multivariate function ⋮ Superposition, reduction of multivariable problems, and approximation ⋮ ExSpliNet: An interpretable and expressive spline-based neural network ⋮ Hilbert 13: Are there any genuine continuous multivariate real-valued functions? ⋮ Spaces \(\ell\)-dominated by \(I\) or \(\mathbb{R}\) ⋮ Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem ⋮ Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximative versions of Kolmogorov's superposition theorem, proved constructively
• An improvement in the superposition theorem of Kolmogorov
• Implications and applications of Kolmogorov's superposition theorem
• Dimension of metric spaces and Hilbert’s problem 13
• On the Structure of Continuous Functions of Several Variables

This page was built for publication: On a constructive proof of Kolmogorov's superposition theorem