Discrete restricted Boltzmann machines

MaRDI QIDQ5502128zbMATH OpenFDO

Authors Guido Montúfar, Jason Morton

Publication date 17 August 2015

Full work available at URL https://arxiv.org/abs/1301.3529, http://jmlr.csail.mit.edu/papers/v16/montufar15a.html

zbMATH Keywords

distributed representationBoltzmann machinerepresentational powerexpected dimensionnaïve Bayes model

Mathematics Subject Classification ID

Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05) Graphical methods in statistics (62A09)

Abstract: We describe discrete restricted Boltzmann machines: probabilistic graphical models with bipartite interactions between visible and hidden discrete variables. Examples are binary restricted Boltzmann machines and discrete naive Bayes models. We detail the inference functions and distributed representations arising in these models in terms of configurations of projected products of simplices and normal fans of products of simplices. We bound the number of hidden variables, depending on the cardinalities of their state spaces, for which these models can approximate any probability distribution on their visible states to any given accuracy. In addition, we use algebraic methods and coding theory to compute their dimension.

Recommendations

• Restricted Boltzmann machines: introduction and review
• Restricted Boltzmann machines as models of interacting variables
• scientific article; zbMATH DE number 6542830
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Learning restricted Boltzmann machines via influence maximization

Cited in

(14)

• Tractable multivariate binary density estimation and the restricted Boltzmann forest
• Restricted Boltzmann machines: introduction and review
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Privacy-preserving restricted Boltzmann machine
• Sampling the Riemann-theta Boltzmann machine
• scientific article; zbMATH DE number 6542830 (Why is no real title available?)
• Deep learning the Ising model near criticality
• When does a mixture of products contain a product of mixtures?
• Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units
• Dimension of Marginals of Kronecker Product Models
• Hierarchical models as marginals of hierarchical models
• Decreasing the size of the restricted Boltzmann machine
• Restricted Boltzmann machines as models of interacting variables
• Hardness of identity testing for restricted Boltzmann machines and Potts models

Describes a project that uses

Uses Software

• darch

This page was built for publication: Discrete restricted Boltzmann machines

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5502128)