An elman neural network with mulltiple inputs

Hi,

I am trying to code an elman neural network with 2 inputs, and one output (size 1).

The size of the first input is 3 - a time delayed signal with 3 historical values

The size of the second input is 2 .

X = Time_Delayed_Input_Signal; % 1 x 100
Z = Input_vector; % 2 x 100
T = Target_Values; % 1 x 100

delays = 3;

net = elmannet(1:2,10);
net = adddelay(net,delays);

net.numinputs = 2;
net.inputConnect = [1 1; 0 0];
net = configure(net,{X;X});
net.inputs{1}.size = delays;
net.inputs{2}.size = 2;
view(net)
[Xs,Xi,Ai] = preparets(net,{X;Z},T) % this is where things go wrong
Y = net(Xs,Xi,Ai);

As always, thanks for any help

Sincerely,

Septimus

Answer 1

[Mahesh Taparia]

Hi

You can use the elmannet as folllows:

net = elmannet(1:3,10); %%% NumDelays=3
[Xs,Xi,Ai,Ts] = preparets(net,X,T);
net = train(net,Xs,Ts,Xi,Ai);
view(net)
Y = net(Xs,Xi,Ai);
perf = perform(net,Ts,Y)

Hope it will help.