SANN - Subsampling - RBF Tab

You can select the RBF tab of the SANN - Subsampling dialog box to access the options described here. For information on the options that are common to all tabs, see SANN - Subsampling. Note that this tab is only available when the Radial basis functions (RBF) option button is selected on the Quick tab of the SANN - Subsampling dialog box.

Note: The options on this tab affect the hidden-output layer weights only (that is, the weights connecting the radial basis functions in the hidden layer to the outputs of the RBF network) and only when the output activations are other than the identity function. The basis functions centers and spreads are fixed in a separate training process. See Network Training for more details.
Option Description
Cycles Specifies the number of training cycles for the network. In each training cycle, the entire training set is passed through the networks and the network error is calculated. This information is then used to adjust the weights so that the error is further reduced. Note that for RBF networks, this option is only available for classification type analyses when the Cross entropy error function is selected on the Quick tab.
Stopping conditions Use the options in this group box to specify when to apply the stopping conditions for early stopping of network training. Note that for RBF networks, these options are only available for classification type analyses when the Cross entropy error function is selected on the Quick tab.
Note: Although SANN defaults to using the training set for early stopping when no test sample is selected, it is still possible to use the training set for that purpose while also having a test sample. To do so, select a validation set (instead of a test set). The only difference between test and validation sets is that the former is used for early stopping while the latter is never presented to the network while training is in progress. So, by having a validation set, you effectively have a test set while using the training sample for early stopping.
Apply stopping conditions Select the check box to implement early stopping to the training of the neural network. Early stopping is applied when the conditions defined below are met by the training algorithm.
Change in error When stopping conditions are applied, network training ends if the average network error improvement over a specified number of training cycles is less than the error improvement value specified here.
Window You can enter the number of training cycles over which the average improvement in network error must be at least as large as the specified error improvement.
Network initialization Use the options in this group to specify how the weights should be initialized at the beginning of training. You can select Normal randomization or Uniform randomization. In addition to selecting a distribution, you must also specify the Mean/Min and Variance/Max to use. You can change the default Mean/Min and Variance/Max settings, but it is generally recommended that you set the Mean/Min to zero and Variance/Max to no more than 0.1. This helps the network to gradually grow from its linear state (small weight values) to the nonlinear (large weight values) mode for modeling input-target relationship as and when necessary during the training process.
Normal randomization Uses a normal randomization of weights for the neural network model. A normal distribution is used to draw the initial weight values.
Uniform randomization Uses a uniform randomization of weights for the neural network model. A uniform distribution is used to draw the initial weight values.
Mean/Min Specifies either the mean (for the normal distribution) or the minimum value (for the uniform distribution) to use for drawing the initial (that is, before training starts) weight sample.
Variance/Max Specifies either the variance (for the normal distribution) or the maximum value (for the uniform distribution) to use for drawing the initial (that is, before training starts) weight sample.