help me ?? How many layers are hidden ? Is it Backpropagation network ?

How many layers are hidden ? Is it Backpropagation network ?

net = newff(minmax(alphabet),[S1 10 S2],{'logsig' 'logsig' 'logsig' },'traingdx');

net.LW{2,1} = net.LW{2,1}*0.01;

net.b{2} = net.b{2}*0.01;

net.performFcn = 'mse';

net.trainParam.show = 20;

net.trainParam.epochs = 2000;

net.trainParam.mc = 0.95;

P = alphabet;

T = targets;

[net,tr] = train(net,P,T);

[JESUS DAVID ARIZA ROYETH]

who are alphabet, S2, S2 and targets? net is a feed-forward backpropagation network

[Ameer Hamza]

This question is a duplicate of your previous question. It is not a good practice to start duplicate question because it wastes the time of volunteers trying to answer your question. You should try to follow the discussion on the original question. That is why we have comment sections on this website.

Answer 1

[Ameer Hamza]

The defined nets will have 4 layers (3 hidden layers), and use traindx which is a Backpropagation training algorithm.

As I already mentioned in your previous question, the newff is obsolete and should no longer be used.