Loss function value trajectories calculated on training and validation data for versions of IntroUNET with different values of the label smoothing strength parameter alpha.

All tests were calculated on simulated examples of the simple bidirectional scenario described in the Methods. Note that for alpha = 0.1 training loss is higher than validation loss. This is because label smoothing is only applied during training, and smoothing increases loss by adding noise to the target y values.

(PDF)