(29th-Nov-2020)
• Invented under the name harmonium ( , ), restricted Boltzmann Smolensky 1986 machines are some of the most common building blocks of deep probabilistic models. We have briefly described RBMs previously, in section . Here we review the 16.7.1 previous information and go into more detail. RBMs are undirected probabilistic graphical models containing a layer of observable variables and a single layer of latent variables. RBMs may be stacked (one on top of the other) to form deeper models. See figure for some examples. In particular, figure a shows the 20.1 20.1 graph structure of the RBM itself. It is a bipartite graph, with no connections permitted between any variables in the observed layer or between any units in the latent layer.
Comentários