S1=10;
[alphabet,targets]=prprob;
[R,Q]=size(alphabet);% alphabet在prprob函數中有定義
[S2,Q]=size(targets); % targets在prprob函數中有定義
P=alphabet;
net=newff(minmax(P),[S1 S2],{'logsig' 'logsig'},'traingdx');
net.LW{2,1}=net.LW{2,1}*0.01;
net.b{2}=net.b{2}*0.01;

netn=net;
netn.trainParam.goal=0.6;
netn.trainParam.epochs=300;
T=[targets targets targets targets];
for pass=1:10
P=[alphabet, alphabet, ...
(alphabet+randn(R,Q)*0.1), ...
(alphabet+randn(R,Q)*0.2)];
[netn,tr]=train(netn,P,T);
end

noise_range=0:0.05:0.5;
max_test=100;
T=targets;
for i=1:11
  noiselevel(i)=noise_range(i);
  errors1(i)=0;
  errors2(i)=0;
  for j=1:max_test
    P=alphabet+randn(35,26)*noiselevel(i); % 測試未經誤差訓練的網絡
    A=sim(net,P);
    AA=compet(A);
    errors1(i)=errors1(i)+sum(sum(abs(AA-T)))/2; % 測試經過誤差訓練的網絡
    An=sim(netn,P);
    AAn=compet(An);
    errors2(i)=errors2(i)+sum(sum(abs(AAn-T)))/2;
   end
end
pause
figure
plot(noise_range,errors1*100,'--',noise_range,errors2*100);
title('識別錯誤率');
xlabel('噪聲指標');
ylabel('未經誤差訓練的網絡 - -   經過誤差訓練的網絡---');