A Boltzmann machine is a probabilistic graphic model that can be interpreted as a stochastic neural network. Boltzmann machines were first introduced in 1985 by Geoffrey Hinton and Terry Sejnowski. It being stochastic is due to the behavior of the neurons; within them, in the activation function, they will have a probabilistic value that will influence the activation of the neuron.
In practice, a Boltzmann machine is a model (including a certain number of parameters) that, when applied to a data distribution, is able to provide a representation. This model can be used to extract important aspects of an unknown distribution (target distribution) starting only from a sample of the latter. The data samples referred ...
