Skip to main content
. 2018 May 21;8:7911. doi: 10.1038/s41598-018-26350-3

Figure 6.

Figure 6

The above figure shows the basis upon which the final network architecture was chosen. (a) Shows that using the GDL is superior to the WCE; (b) shows that having a convolutional layer as the first layer is superior to an MDLSTM layer; (c) and (d) show that using 32 units and 2 layers, respectively, produces, on average, the strongest network.