Equilibrium and non-equilibrium regimes in the learning of restricted Boltzmann machines*

DOI10.1088/1742-5468/ac98a7OpenAlexW3164698142MaRDI QIDQ5055423

Cyril Furtlehner, Aurélien Decelle, B. Seoane

Publication date: 13 December 2022

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.13889

zbMATH Keywords

machine learningmemory effects

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items (1)

An introduction to machine learning: a perspective from statistical physics

Uses Software

• CIFAR

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Training restricted Boltzmann machines: an introduction
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Algorithms for estimating the partition function of restricted Boltzmann machines
• Restricted Boltzmann machines: introduction and review
• Training Products of Experts by Minimizing Contrastive Divergence
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• ‘Place-cell’ emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space

This page was built for publication: Equilibrium and non-equilibrium regimes in the learning of restricted Boltzmann machines*