Deep learning the Ising model near criticality

MaRDI QIDQ4558488zbMATH OpenFDO

Authors Alan Morningstar, R. G. Melko

Publication date 22 November 2018

Full work available at URL https://arxiv.org/abs/1708.04622, http://jmlr.csail.mit.edu/papers/v18/17-527.html

zbMATH Keywords

deep learningrestricted Boltzmann machinedeep belief networkdeep Boltzmann machine

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Neural nets and related approaches to inference from stochastic processes (62M45) Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20)

Recommendations

• An efficient learning procedure for deep Boltzmann machines
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• The solution of the deep Boltzmann machine on the Nishimori line
• Annealing and replica-symmetry in deep Boltzmann machines
• Why does deep and cheap learning work so well?

Cites work

• scientific article; zbMATH DE number 1782878 (Why is no real title available?)
• A Fast Learning Algorithm for Deep Belief Nets
• An efficient learning procedure for deep Boltzmann machines
• Crystal Statistics. I. A Two-Dimensional Model with an Order-Disorder Transition
• Discrete restricted Boltzmann machines
• Reducing the Dimensionality of Data with Neural Networks
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Solving the quantum many-body problem with artificial neural networks
• Statistics of the Two-Dimensional Ferromagnet. Part I
• Training Products of Experts by Minimizing Contrastive Divergence

Cited in

(11)

• Machine learning as a universal tool for quantitative investigations of phase transitions
• On dissipative symplectic integration with applications to gradient-based optimization
• A universal training scheme and the resulting universality for machine learning phases
• scientific article; zbMATH DE number 7370576 (Why is no real title available?)
• Equilibrium and non-equilibrium regimes in the learning of restricted Boltzmann machines*
• Reconstruction of pairwise interactions using energy-based models*
• The Ising model with hybrid Monte Carlo
• Canonical Monte Carlo multispin cluster method
• Study of phase transition of Potts model with domain adversarial neural network
• p-Adic statistical field theory and convolutional deep Boltzmann machines
• Sharp threshold for the Ising perceptron model

Describes a project that uses

Uses Software

• darch

This page was built for publication: Deep learning the Ising model near criticality

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558488)