Model Summary (neural networks)

The Model Summary view is a snapshot, at-a-glance summary of the neural network predictive or classification accuracy.

Model summary. The table identifies the target, the type of neural network trained, the stopping rule that stopped training (shown if a multilayer perceptron network was trained), and the number of neurons in each hidden layer of the network.

Neural Network Quality. The chart displays the accuracy of the final model, which is presented in larger is better format. For a categorical target, this is simply the percentage of records for which the predicted value matches the observed value. For a continuous target, the accuracy is given as the R² value.

Multiple targets. If there are multiple targets, then each target is displayed in the Target row of the table. The accuracy displayed in the chart is the average of the individual target accuracies.