Deep Belief Nets in C++ and CUDA C: Volume 1: Restricted Boltzmann Machines and Supervised Feedforward Networks

© Timothy Masters 2018

Timothy MastersDeep Belief Nets in C++ and CUDA C: Volume 1https://doi.org/10.1007/978-1-4842-3591-1_3

3. Restricted Boltzmann Machines

Timothy Masters¹ 

(1)

Ithaca, New York, USA

 

This chapter explores what is probably the most common building block of deep belief nets: the restricted Boltzmann machine (RBM). There are numerous excellent treatments of RBMs; my favorite “introduction” is Learning Deep Architecture for AI by Yoshua Bengio (Now Publishers, 2009) because the discussion, though relatively short, is enclosed in fabulous background and supplementary material. When it comes to practical aspects of training RBMs, “A Practical Guide to Training Restricted Boltzmann Machines” by Geoffrey Hinton (2010) can’t be beat. Also, ...