DL4J Feedforward Predictor (Regression) (legacy)

This node creates a regression prediction using the supplied network and test data. The node is intended to be used with the DL4J Feedforward Learner (Regression) node. The output is a column for each target feature containing the predicted value.

The KNIME Deeplearning4J Integration has been marked as legacy with KNIME Analytics Platform 5.0 and will be deprecated in a future version. If you are using this extension in a production workflow, consider switching to one of the other deep learning integrations available in KNIME Analytics Platform.

Options

Change prediction column/s name?
Allows to change the name of the prediction column/s. Here you can enter a pattern specifying the new name of the prediction column. The pattern needs to contain '$1' which will be replaced by the corresponding column name. E.g. if there are two target columns with the names 't1' and 't2' the pattern 'Prediction ($1)' will evaluate to the column names 'Prediction (t1)' and 'Prediction (t2)'.

Input Ports

Icon
Regression Deep Learning Model.
Icon
Data table containing testing data.

Output Ports

Icon
Input data with prediction columns.

Views

This node has no views

Workflows

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.