This command trains a backpropagation network using the Matlab style of training algorithm. The method is based on a global learning rate parameter with a momentum term. By default one neuron for each input is used.
Example (ex5.7): Train a three-layered (input + hidden + output layer) network with a sine function using a sigmoid activation function in neurons. After training save the network output.
NDA> load sin.dat NDA> select sinx -f sin.x NDA> select siny -f sin.y NDA> mbp -di sinx -do siny -net 3 1 10 1 -types s s s -em 1000 -nout wei -ef virhe -bs 0.2 -mom 0.1 NDA> fbp -di sinx -do out -win wei NDA> select output -f sin.x out.0 NDA> save output