The interface stores the training data for each class as a separate map layer. In the use of the tool, the user is asked to enter the name of the output map layer, the number of output classes, and the names of the input map layers.
However 20% of randomly selected training data records were also not used for the real training, they represented the testing data used for early stopping.
A powerful additional feature lets radiators be automatically sized and positioned in groups of rooms, using constraining data such as sizing strategy, maximum length, and so forth.
However, if misclassified samples are used in the training process, these erroneous samples may be grouped as a separate undesired subclass. Therefore, care should be taken to provided accurate training data.
See also: Class, Algorithm, Model, Layer, Layers