Skip to main content
. 2021 Sep 2;16(9):e0256997. doi: 10.1371/journal.pone.0256997

Fig 1. Mean average error over 1000 training epochs.

Fig 1

Mean average error of the neural network, i.e. the average difference between the true and predicted author H-Index, for each epoch. After around 400 epochs, the network starts to overfit to the training data, as the training error rate continues to go down, while the validation error rate (shown as a dotted line) remains roughly constant.