A three layer neural network can represent any multivariate function

DOI10.1016/j.jmaa.2023.127096OpenAlexW4319923063MaRDI QIDQ2697707

Vugar E. Ismailov

Publication date: 13 April 2023

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.03016

zbMATH Keywords

indicator functionlinear functionalZorn's lemmaLipschitz functionKolmogorov's superposition theorem

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Functions of several variables (26Bxx) Approximations and expansions (41Axx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the approximation by neural networks with bounded number of neurons in hidden layers
• A note on the representation of continuous functions by linear superpositions
• On a constructive proof of Kolmogorov's superposition theorem
• Lower bounds for approximation by MLP neural networks
• A universal mapping for Kolmogorov's superposition theorem
• Computational aspects of Kolmogorov's superposition theorem
• Multilayer feedforward networks are universal approximators
• On the uniqueness of representation by linear superpositions
• Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem
• On the representation by linear superpositions
• An improvement in the superposition theorem of Kolmogorov
• Ridge Functions and Applications in Neural Networks
• Superposition, reduction of multivariable problems, and approximation
• On the Structure of Continuous Functions of Several Variables
• Neural network approximation: three hidden layers are enough
• The Kolmogorov-Arnold representation theorem revisited

This page was built for publication: A three layer neural network can represent any multivariate function