multilayerperceptronnode properties

Last updated: Jan 18, 2024

Multilayer perceptron is a classifier based on the feedforward artificial neural network and consists of multiple layers. Each layer is fully connected to the next layer in the network. The MultiLayerPerceptron-AS node in SPSS Modeler is implemented in Spark. For details about the multilayer perceptron classifier (MLPC), see https://spark.apache.org/docs/latest/ml-classification-regression.html#multilayer-perceptron-classifier.

Table 1. multilayerperceptronnode properties
`multilayerperceptronnode` properties	Data type	Property description
`custom_fields`	boolean	This option tells the node to use field information specified here instead of that given in any upstream Type node(s). After selecting this option, specify the following fields as required.
`target`	field	One field name for target.
`inputs`	field	List of the field names for input.
`num_hidden_layers`	string	Specify the number of hidden layers. Use a comma between multiple hidden layers.
`num_output_number`	string	Specify the number of output layers.
`random_seed`	integer	Generate the seed used by the random number generator.
`maxiter`	integer	Specify the maximum number of iterations to perform.
`set_expert`	boolean	Select the Expert Mode option in the Model Building section if you want to specify the block size for stacking input data in matrices.
`block_size`	integer	This option can speed up the computation.
`use_model_name`	boolean	Specify a custom name for the model or use `auto`, which sets the label as the target field.
`model_name`	string	Renamed model name.