训练好的权值、阈值的输出方法是:
输入到隐层权值: w1=net.iw{1,1}
隐层阈值: theta1=net.b{1}
隐层到输出层权值: w2=net.lw{2,1};
输出层阈值: theta2=net.b{2}
P=[];
T=[];
net=newff(minmax(P),[4,1],{'tansig','purelin'},'traingda');
net.trainParam.epochs=500;
net.trainParam.goal=0.001;
net=train(net,P,T);
save net;
net.lw{1,1}表示输入到隐含层权值;net.lw{2,1}表示隐含层到输出层的权值