Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines

DOI10.1162/NECO_A_00113zbMath1274.62128arXiv1005.1593WikidataQ47323275 ScholiaQ47323275MaRDI QIDQ3015455

Guido Montúfar, Nihat Ay

Publication date: 13 July 2011

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

Full work available at URL: https://arxiv.org/abs/1005.1593

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Approximations to statistical distributions (nonasymptotic) (62E17)

Related Items (10)

Hierarchical models as marginals of hierarchical models ⋮ Exploiting layerwise convexity of rectifier networks with sign constrained weights ⋮ Dimension of Marginals of Kronecker Product Models ⋮ Approximation Analysis of Convolutional Neural Networks ⋮ Training restricted Boltzmann machines: an introduction ⋮ An Infinite Restricted Boltzmann Machine ⋮ Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units ⋮ Approximation properties of Gaussian-binary restricted Boltzmann machines and Gaussian-binary deep belief networks ⋮ Mixture decompositions of exponential families using a decomposition of their sample spaces ⋮ When Does a Mixture of Products Contain a Product of Mixtures?

Cites Work

• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Deep, Narrow Sigmoid Belief Networks Are Universal Approximators
• Deep Belief Networks Are Compact Universal Approximators
• A Fast Learning Algorithm for Deep Belief Nets
• The measure of the critical values of differentiable maps

This page was built for publication: Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines