Figure 1

The figure indicates the percentage change in test MAE of the proposed BRNet w.r.t (a) AutoML, (b) ElemNet, and (c) IRNet. The x-axis shows the dataset size on a log scale, and the y-axis shows the percentage change in test MAE from all the model training performed in Tables 2 and 3 calculated as ((MAE\(_{BRNet}\)/MAE\(_{Other})-1\)) \(\times\) 100\(\%\).