SANN - Results - Predictions (Kohonen) Tab

Neural Networks

Select the Predictions (Kohonen) tab of the SANN - Results dialog box to access the options described here. This tab is only available for cluster analysis models. For information on the options that are common to all tabs, see SANN - Results.

Predictions spreadsheet. Use the options in this group box to configure and display the predictions spreadsheet. The variables and cases contained in the spreadsheet are dependent on selections made in the Include group box (see below) and the Sample group box.

Include. Use the options in this group box to (optionally) include additional information in the predictions spreadsheet.

Inputs. Select this check box to include the input variables in the Predictions spreadsheet.

Winning neuron position. Select this check box to include the winning neuron position in the Predictions spreadsheet.

Winning neuron activation. Select this check box to include the winning neuron activations in the Predictions spreadsheet. The activation of a neuron is the Euclidean distance between the input and weight vectors of the neuron. This check box is selected by default.

Variables. Select this check box to include an arbitrary selection of variables from the data set in the Predictions spreadsheet. If you click the Predictions button when this check box is selected, a variable selection dialog box will be displayed, enabling you to select the variables to include in the spreadsheet. Note that this check box is only enabled if there are variables in the data set that have not been used in the analysis.

Predictions. Click the Predictions button to display the predictions spreadsheet for each active model. The precise details shown in the spreadsheet are controlled by the options selected in the Include group box and selections made in the Sample group box.

Weights. Click the Weights button to display a spreadsheet of weights for each model in the Active neural networks grid.

Data statistics. Click the Data statistics button to generate a spreadsheet containing the mean, standard deviation, minimum value and maximum value for each variable in the analysis. These data statistics will be broken down by each sample (training, testing, and validation) and also reported for the overall data set.

Single predictions. Use the options in this group box to view the activations for a single data case.

Datacase. Enter a number in this box to specify a case from the data set. The case is fed as input to the network.

Activations. Click the Activations button with the spreadsheet icon to generate a results spreadsheet of activations for the currently selected case.

Activations. Click the Activations button with the graph icon to plot a bivariate histogram of the activations for the currently selected case.

Frequencies. Click the Frequencies button to plot a bivariate histogram of topological frequencies for each active model. Note that the cases used in the bivariate histogram are determined by selections in the Sample group box.

Frequency. Click the Frequency button to display a spreadsheet of topological frequencies for the active models. The results in the spreadsheet can be broken down by samples (or combinations of samples) using the options in the Sample group box.