% 用GA訓練BP網絡的權值、閾值
tic, % 開始計時
[P,T,R,S1,S2,S]=nninit; % BP網絡初始化
aa=ones(S,1)*[-1 1];
popu=60; % 初始種群個數
initPpp=initializega(popu,aa,'gabpEval');
gen=700; % 遺傳代數
[x endPop bPop trace]=ga(aa,'gabpEval',[],initPpp,[1e-6 1 1],'maxGenTerm',gen,...
  'normGeomSelect',[0.09],['arithXover'],[2],'nonUnifMutation',[2 gen 3]);
%%Lets take a look at the performance of the ga during the run
subplot(2,1,1)
plot(trace(:,1),1./trace(:,3),'r-')
hold on
plot(trace(:,1),1./trace(:,2),'b-')
xlabel('Generation');
ylabel('Sum-Squared Error');
subplot(2,1,2)
plot(trace(:,1),trace(:,3),'r-')
hold on
plot(trace(:,1),trace(:,2),'b-')
xlabel('Generation');
ylabel('Fittness');
% 從編碼x中解碼出BP網絡所對應的權值、閾值
[W1 B1 W2 B2]=gadecod(x); 
% 仿真結果
TT=simuff(P,W1,B1,'tansig',W2,B2,'purelin')
E=sum((T-TT).^2)./10;
E=sqrt(E)
e1=(T-TT)./T
c=poststd(TT,meant,stdt)
toc % 結束計時
xk1=input('     please input .....xk==')
  pnew=xk1';
  pnew=trastd(pnew,meanp,stdp);%將數據通過自標準化再用來輸入網絡
  an=simuff(pnew,W1,B1,'tansig',W2,B2,'purelin')%網絡模擬出來的值
  anew=poststd(an,meant,stdt)%模擬出的值再線性返回樣本預測值
  tk1=input('     please input .....tk==')
  e2=(tk1-anew)./tk1
  xk2=input('     please input .....xk==')
  pnew=xk2';
  pnew=trastd(pnew,meanp,stdp);%將數據通過自標準化再用來輸入網絡
  an=simuff(pnew,W1,B1,'tansig',W2,B2,'purelin')%網絡模擬出來的值
  anew=poststd(an,meant,stdt)%模擬出的值再線性返回樣本預測值
  tk2=input('     please input .....tk==')
  e2=(tk2-anew)./tk2