Backprop

Backprop is a standard form of supervised learning. It is perhaps the best known and most popular means of training neural networks. The backprop trainer can be configured in the trainer dialog. It is primarily used by the backprop network and simple recurrent network, though it can also be used by scripts and in other ways.

Currently the following parameters can be set:

Learning Rate: A standard learning rate. This determines how quickly synapses change.

Momentum: This scales the rate of weight change by the amount a given weight changed on the previous time step. This speeds up learning and prevents oscillations. Momentum should be between 0 and 1; 0.9 is a common value.