Decreasing the size of the restricted Boltzmann machine

DOI10.1162/NECO_A_01176zbMATH Open1476.68238arXiv1807.02999OpenAlexW2860169200WikidataQ91588978 ScholiaQ91588978MaRDI QIDQ5154145FDOQ5154145

Authors: Yohei Saito, Takuya Kato 

Publication date: 1 October 2021

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

Abstract: We propose a method to decrease the number of hidden units of the restricted Boltzmann machine while avoiding decrease of the performance measured by the Kullback-Leibler divergence. Then, we demonstrate our algorithm by using numerical simulations.

Full work available at URL: https://arxiv.org/abs/1807.02999

Recommendations

• An infinite restricted Boltzmann machine
• Restricted Boltzmann machines
• Restricted Boltzmann machines: introduction and review
• Training restricted Boltzmann machines: an introduction
• Discrete restricted Boltzmann machines

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Reducing the Dimensionality of Data with Neural Networks
• Title not available (Why is that?)
• Training Products of Experts by Minimizing Contrastive Divergence
• A Fast Learning Algorithm for Deep Belief Nets
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• An efficient learning procedure for deep Boltzmann machines
• Solving the quantum many-body problem with artificial neural networks
• Learning compositional representations of interacting systems with restricted Boltzmann machines: comparative study of lattice proteins

Uses Software

• darch
• MNIST
• Tensor2Tensor
• WaveNet

This page was built for publication: Decreasing the size of the restricted Boltzmann machine

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5154145)