Skip to main content
. 2019 Jan 8;9:1147. doi: 10.3389/fneur.2018.01147

Figure 6.

Figure 6

Training and validation loss over epochs obtained by training a CNN model using (A) Patlak and (B) eTofts model parameters. Gradual decrease in the loss indicates the efficiency of the network for learning useful representations related to the underlying mapping between the input and output.