Approximation properties of Gaussian-binary restricted Boltzmann machines and Gaussian-binary deep belief networks

DOI10.1016/J.NEUNET.2022.05.020WikidataQ114145548 ScholiaQ114145548MaRDI QIDQ6488716

Linyan Gu, Feng Zhou, Lihua Yang

Publication date: 17 October 2023

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

zbMATH Keywords

approximation theoryfeedforward neural networkGaussian-binary deep belief networksGaussian-binary restricted Boltzmann machines

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximations and expansions (41-XX)

Cites Work

• Density estimation through convex combinations of densities: Approximation and estimation bounds
• Multilayer feedforward networks are universal approximators
• Nonlinear approximation via compositions
• Error bounds for approximations with deep ReLU networks
• Hierarchical models as marginals of hierarchical models
• Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines
• Reducing the Dimensionality of Data with Neural Networks
• Training Products of Experts by Minimizing Contrastive Divergence
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Deep Belief Networks Are Compact Universal Approximators
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

This page was built for publication: Approximation properties of Gaussian-binary restricted Boltzmann machines and Gaussian-binary deep belief networks