Skip to main content
. 2019 Nov 22;10:1182. doi: 10.3389/fgene.2019.01182

Figure 2.

Figure 2

Graph embedding deep feedforward network (GEDFN). The graph embedding layer (first hidden layer) has same neurons with the input layer. The sparse connect between the input layer and the first hidden layer is marked as black. Other hidden layers are fully-connected.