p= 0.229 0.336 0.381 0.406 0.422 0.433 0.441 0.447 0.452 0.456 0.459 0.462 0.464 0.466;0.229 0.336 0.381
0.406 0.422 0.433 0.441 0.447 0.452 0.456 0.459 0.462 0.464 0.466;0.344 0.504 0.572 0.61 0.634 0.65
0.662 0.671 0.678 0.684 0.689 0.693 0.696 0.699; …;0.274 0.402 0.456 0.486 0.505 0.518 0.527 0.535 0.54
0.545 0.549 0.552 0.555 0.557;0.346 0.507 0.576 0.614 0.638 0.654 0.666 0.675 0.682 0.688 0.693 0.697
0.701 0.703
t=[0.274 0.336 0.461 0.56 0.563 0.624 0.614 0.535 0.548 0.563 0.539 0.462 0.469 0.502]
net=newff([0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1; 0 1;
0 1; 0 1; 0 1], ,{'logsig','logsig'},'trainlm');
net=init(net);
net.trainParam.show=100;
net.trainParam.lr=0.1;
net.trainParam.epochs=1000;
net.trainParam.goal=1e-5;
net,tr]=train(net,p,t);
a = sim(net,p);
Algorithm 2: The back propagation network program.