Backprop Network

Backprop is a standard form of supervised learning.   It is perhaps the best known and most popular means of training neural networks.

An example which steps through the process of  creating and trainining a backprop network is in the examples page.

Creation Dialog

Number of Layers

Number of Neurons

Neuron Type

Tanh

Logistic

Linear

After selecting Insert > Insert Network > Backrpop, a dialog will appear asking that you specify a topology, which means how many layers, and how many neurons per layer (from bottom to top layer). 

Right Click Menu

Edit/Train Backprop

Rename

Remove Network

View/Edit Data


Training

Training a network involves specifying input data, target data, and then running the algorithm.  This process is covered here.

Parameters

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.