Stopping Rules (neural networks)

Figure 1. Stopping Rules settings
Stopping Rules settings

These are the rules that determine when to stop training multilayer perceptron networks; these settings are ignored when the radial basis function algorithm is used. Training proceeds through at least one cycle (data pass), and can then be stopped according to the following criteria.

Use maximum training time (per component model). Choose whether to specify a maximum number of minutes for the algorithm to run. Specify a number greater than 0. When an ensemble model is built, this is the training time allowed for each component model of the ensemble. Note that training may go a bit beyond the specified time limit in order to complete the current cycle.

Customize number of maximum training cycles. The maximum number of training cycles allowed. If the maximum number of cycles is exceeded, then training stops. Specify an integer greater than 0.

Use minimum accuracy. With this option, training will continue until the specified accuracy is attained. This may never happen, but you can interrupt training at any point and save the net with the best accuracy achieved so far.

The training algorithm will also stop if the error in the overfit prevention set does not decrease after each cycle, if the relative change in the training error is small, or if the ratio of the current training error is small compared to the initial error.