The target block represents the output that we are trying to learn with our model. As for the input block, after placing a target block we have to assign a feature to it; typically a single variable is used as output, be it a label (classification), a scalar (regression) or an image (autoencoders, image segmentation).
Feature: the feature assigned to the Target block. This can be an imported feature or a combined feature.
Loss function: the loss function to be used in training (see the documentation for loss functions).