| continue |
2010-05-03 22:43 |
新手求助~（关于初级的神经网络问题）
各位大虾，我在网上看到的教程里的一个程序段，本来想要试试看的： 6>e YG <y{
net=newff([-1 2; 0 5],[3,1],{'tansig','purelin'},'traingd'); Qh {]gw-6
net.trainParam.show = 50; O{&wqV5m"
net.trainParam.lr = 0.05; hcrx(oJ5
net.trainParam.epochs = 300; :/6gGU>pu
net.trainParam.goal = 1e-5; _usi~m
p = [-1 -1 2 2;0 5 0 5]; G
]JWd
t = [-1 -1 1 1]; Z.{r%W{ 2
net=train(net,p,t); R2B0?fu
TRAINGD, Epoch 0/300, MSE 1.59423/1e-05, Gradient 2.76799/1e-10 2nv-/ %]
TRAINGD, Epoch 50/300, MSE 0.00236382/1e-05, Gradient 0.0495292/1e-10 _VFL}<i
TRAINGD, Epoch 100/300, MSE 0.000435947/1e-05, Gradient 0.0161202/1e-10 D Kng.P
TRAINGD, Epoch 150/300, MSE 8.68462e-05/1e-05, Gradient 0.00769588/1e-10 s]@k, %
TRAINGD, Epoch 200/300, MSE 1.45042e-05/1e-05, Gradient 0.00325667/1e-10 &h67LMD!
TRAINGD, Epoch 211/300, MSE 9.64816e-06/1e-05, Gradient 0.00266775/1e-10 c&>==pI]k
TRAINGD, Performance goal met. bA*T1Db,t>
a = sim(net,p) ATq-&1 hs
plot(p,t,p,a,'o') >G<.^~o
但是为什么老是报错： nv-_\M
??? Input argument "net" is undefined. =2tl149m/z
|
|