Stochastic Feedforward Neural Networks: Universal Approximation

DOI10.1017/9781009025096.007OpenAlexW2981726190MaRDI QIDQ5879780FDOQ5879780

Authors: Thomas Merkh, Guido Montúfar 

Publication date: 6 March 2023

Full work available at URL: https://arxiv.org/abs/1910.09763

Recommendations

• Deep, Narrow Sigmoid Belief Networks Are Universal Approximators
• Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines
• Deep belief networks are compact universal approximators
• Universal approximation bounds for superpositions of a sigmoidal function
• Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cited In (5)

• Title not available (Why is that?)
• The dynamic universality of sigmoidal neural networks
• Lu decomposition and Toeplitz decomposition of a neural network
• Deep belief networks are compact universal approximators
• Deep, Narrow Sigmoid Belief Networks Are Universal Approximators

This page was built for publication: Stochastic Feedforward Neural Networks: Universal Approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5879780)