Skip to main content
. 2018 Sep 20;9:1036. doi: 10.3389/fphar.2018.01036

Figure 4.

Figure 4

t-SNE visualization of the output of each layer in the deep neural network. Positive and negative samples are marked as green and red points, respectively. (A) input layer; (B) the first encoder layer; (C) the second encoder layer; (D) the third encoder layer; (E) the first FC layer; (F) the second FC layer.