Restricted Boltzmann Machine and Deep Belief Network: Tutorial and Survey

TL;DR

This tutorial and survey comprehensively covers Boltzmann Machines, Restricted Boltzmann Machines, and Deep Belief Networks, explaining their structures, training methods, and applications across multiple fields.

Contribution

It provides a detailed overview of the models, training algorithms, and variations, serving as a foundational resource for understanding and applying these probabilistic models.

Findings

Clarifies the structure and training of RBMs and DBNs

Discusses different variable distributions and training methods

Provides insights into applications in various scientific fields

Abstract

This is a tutorial and survey paper on Boltzmann Machine (BM), Restricted Boltzmann Machine (RBM), and Deep Belief Network (DBN). We start with the required background on probabilistic graphical models, Markov random field, Gibbs sampling, statistical physics, Ising model, and the Hopfield network. Then, we introduce the structures of BM and RBM. The conditional distributions of visible and hidden variables, Gibbs sampling in RBM for generating variables, training BM and RBM by maximum likelihood estimation, and contrastive divergence are explained. Then, we discuss different possible discrete and continuous distributions for the variables. We introduce conditional RBM and how it is trained. Finally, we explain deep belief network as a stack of RBM models. This paper on Boltzmann machines can be useful in various fields including data science, statistics, neural computation, and statistical physics.