The size of the data used to train and simulate the network must be same. From the information you provided, it seems that your training and simulation dataset sizes are different. You should find out the training dataset size and accordingly change your simulation data.
Below is an example simulating the same behaviour:
%NN trained using P as dataset
P = [0 1 2 3 4 5 6 7 8 9 10;
0 1 2 3 4 5 6 7 8 9 10];
T = [0 1 2 3 4 3 2 1 2 3 4];
net = newff([0 10; 0 10],[5 1],{'tansig' 'purelin'});
net.trainParam.epochs = 50;
net = train(net,P,T);
save('NN2.mat')
%Trained NN loaded and simulated with data of same dimension
load('NN2.mat')
%Simulation data
simdata = [0 1 2 3 4 8 6 7 8 9 10;
0 1 2 3 4 5 6 7 8 9 10];
input = sim(net, simdata)
Thanks,
Pranav Verma
