Training Window

Qnet 2000

Training Window

The training window is used to view, analyze and interact with the current training run. Use the File option to save training information or exit the current run. Interact with the network training parameters by using the Options menu. Check the training progress with Qnet’s NetGraph and Info tools. Selecting any of these options will suspend network training as indicated on the status bar. Select Training Start/Stop to restart network training.

The information displayed in the training window provides details on the network model, the current training parameters and the training results. The Network Definition Group displays the network’s name, the number of network layers, the number of input nodes, the number of output nodes, the total number of hidden nodes, the number of network connections, the number of training and test patterns, the network size in bytes, the training mode (standard, autotrain, autoload) and the number of the net currently training over the total number of nets being processed (AutoTraining). The Training Controls Group displays the maximum number of iterations for the run, the LRC start iteration, the FAST-Prop coefficient, the learn rate settings, the momentum factor and the screen update, the AutoSave rate and the RMS error that will terminate training. The Training Results Group contains the current iteration, the training and test set RMS errors, training and test set correlation coefficients and the training and test set tolerance percentages. The connections per second benchmark indicates computational speed, the percent complete, and time remaining (based on network training completing the specified number of iterations) are also included. The menu items and user options are organized as follows:

File

Save Network

Save Network As...

Save Outputs/Targets...

Save Error History...

Save AutoSave Network...

Options