Qnet 2000 |
The FAST-Prop coefficient controls the algorithm used by Qnet for training. FAST-Prop training can accelerate training for some networks and training runs can switch between FAST-Prop and backprop methods "on the fly" during training. If the FAST-Prop coefficient is set to 0 (the default), Qnet will employ its backpropagation algorithm to train the network. If the coefficient is set to a value above 0.0 (to a maximum of 3.0), the FAST-Prop algorithm is used. The closer the coefficient is set to 0.0, the closer FAST-Prop approximates standard backpropagation. While the FAST-Prop training method can often accelerate the learning process, a drawback with this method is that there is a risk that this algorithm will not converge to a minimum error, especially when higher coefficient values are used. For this reason, it is recommended that the training algorithm be switched to the standard backpropagation method at some point during the training process. Likewise, the FAST-Prop algorithm is NOT recommended for long periods of unattended training. Whenever FAST-Prop is being used, the training and test set RMS errors should be monitored closely for signs that the network is no longer converging. If either of these error values begin to increase, it is recommended that the FAST-Prop coefficient be set to 0. See Technical Overview for more information