Restricted Boltzmann machine. RBM. BM. ANN

Source:

https://en.m.wikipedia.org/wiki/Restricted_Boltzmann_machine

"RBMs have found applications in:

* dimensionality reduction, 

* classification, 

* collaborative filtering,

* feature learning,

* topic modelling 

* and even many body quantum mechanics. 

They can be trained in either supervised or unsupervised ways, depending on the task.

As their name implies, RBMs are a variant of Boltzmann machines, with the restriction that their neurons must form a bipartite graph: a pair of nodes from each of the two groups of units (commonly referred to as the "visible" and "hidden" units respectively) may have a symmetric connection between them; and there are no connections between nodes within a group. 

By contrast, "unrestricted" Boltzmann machines may have connections between hidden units. 

This restriction allows for more efficient training algorithms than are available for the general class of Boltzmann machines, in particular... 

the gradient-based contrastive divergence algorithm.^"