This workflow shows an example of Active Learning. We read a simple dataset of images separated in two classes and calculate some features on them. Now the "Active Learning Loop" determines the best sample which could be manuallay labeled by a user and benefits most to the separation of the classes. The decision of the best sample is based on a specific score (in this case a "PBAC Scorer"). The samples can be labeled using the view of the "Active Learn Loop End". Execute the loop and open the view while the loop is executing. The view shows the current sample with the best score selected by the Element Selector Node. In the view you can use the "Table Selection" or the "Wizzard" to annotate the sample. In the "Manage Classes" tab you can se an overview of your classes. You can either terminate the loop on your own or label all rows and the loop terminates automatically (corresponding option needs to be checked in the "Active Learn Loop End" configuration).