Learning algorithm for Boltzmann machines using max-product algorithm and pseudo-likelihood

DOI10.4036/IIS.2012.55MaRDI QIDQ4911240zbMATH OpenOpenAlexFDO

Authors Muneki Yasuda, Junya Tannai, Kazuyuki Tanaka

Publication date 14 March 2013

Published in Interdisciplinary Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.4036/iis.2012.55

zbMATH Keywords

deep learningEM algorithmpseudo-likelihood estimationBoltzmann machinemax-product belief propagation

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Learning and adaptive systems in artificial intelligence (68T05) Nonnumerical algorithms (68W05)

Recommendations

• A block successive lower-bound maximization algorithm for the maximum pseudo-likelihood estimation of fully visible Boltzmann machines
• Approximate Learning Algorithm in Boltzmann Machines
• Pseudo temperature of observed data
• Consistency of Pseudolikelihood Estimation of Fully Visible Boltzmann Machines
• scientific article; zbMATH DE number 1928639

Cited in

(7)

• scientific article; zbMATH DE number 1928639 (Why is no real title available?)
• Learning algorithm of Boltzmann machine based on spatial Monte Carlo integration method
• Pseudo temperature of observed data
• Approximate Learning Algorithm in Boltzmann Machines
• A block successive lower-bound maximization algorithm for the maximum pseudo-likelihood estimation of fully visible Boltzmann machines
• Fast recovery algorithm based on Boltzmann machine and MMSE criterion
• Full-span log-linear model and fast learning algorithm

This page was built for publication: Learning algorithm for Boltzmann machines using max-product algorithm and pseudo-likelihood

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4911240)