How does Restricted Boltzmann Machine (RBM) try to model the distribution of data?

173 Views Asked by At

An RBM is a non-directed graphical model that defines the distribution over some input vector X. I know it's going to model the distribution of that those vectors in my training data X using a layer of binary hidden units, but i don't understand if it's an unsupervised method, then what kind of information about the labeling of the data gives us the distribution? I would appreciate if someone could give a brief intuitive explanation about this.