The Kolmogorov-Arnold representation theorem revisited

DOI10.1016/j.neunet.2021.01.020arXiv2007.15884OpenAlexW3127995079MaRDI QIDQ6078698

Johannes Schmidt-Hieber

Publication date: 28 September 2023

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.15884

zbMATH Keywords

function approximationspace-filling curvesdeep ReLU networksKolmogorov-Arnold representation theorem

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximation by other special function classes (41A30)

Related Items (4)

Approximation bounds for norm constrained neural networks with applications to regression and GANs ⋮ Neural network approximation: three hidden layers are enough ⋮ A three layer neural network can represent any multivariate function ⋮ A hybrid partitioned deep learning methodology for moving interface and fluid-structure interaction

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• On a constructive proof of Kolmogorov's superposition theorem
• On best approximation by ridge functions
• On the approximation of functional classes equipped with a uniform measure using ridge functions
• Lower bounds for approximation by MLP neural networks
• Analog computation via neural networks
• Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem
• Nonparametric regression using deep neural networks with ReLU activation function
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Rate-optimal estimation for a general class of nonparametric regression models with unknown link functions
• Deep vs. shallow networks: An approximation theory perspective
• Space-Filling Curves
• Deep Network Approximation Characterized by Number of Neurons
• Nonparametric Regression Based on Hierarchical Interaction Models
• On the Structure of Continuous Functions of Several Variables
• 0n the best approximation by ridge functions in the uniform norm

This page was built for publication: The Kolmogorov-Arnold representation theorem revisited