Skip to main content
. 2014 Jan 30;7:272. doi: 10.3389/fnins.2013.00272

Figure 5.

Figure 5

The RBM network consists of a visible and a hidden layer. The visible layer is partitioned into 784 sensory neurons (vd) and 40 class label neurons (vc) for supervised learning. During data presentation, the activities in the visible layer are driven by a data layer d, consisting of a digit and its label (1 neuron per label). In the RBM, the weight matrix between the visible layer and the hidden layer is symmetric.