新手求助~（关于初级的神经网络问题）

Continue

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：
3 q" l0 I; w( P6 Cnet=newff([-1 2; 0 5],[3,1],{'tansig','purelin'},'traingd');
( E& M: }4 e3 \! E7 ^( t
0 D& M# c  u3 X8 j5 Z2 X: Q
8 ~8 c/ F' }9 s7 Znet.trainParam.show = 50;
net.trainParam.lr = 0.05;
net.trainParam.epochs = 300;
net.trainParam.goal = 1e-5;
( z1 P  O* w0 _. Qp = [-1 -1 2 2;0 5 0 5];
t = [-1 -1 1 1];
. S) ^8 G$ q) x  `& k7 V/ W
% Q9 p* A% V# [! ^
& G- k) t+ P/ I. U4 x9 ?net=train(net,p,t);
TRAINGD, Epoch 0/300, MSE 1.59423/1e-05, Gradient 2.76799/1e-10
' ]8 L) m: L! E7 D

+ a1 O+ [1 Y5 D3 U2 d* KTRAINGD, Epoch 50/300, MSE 0.00236382/1e-05, Gradient 0.0495292/1e-10
" {3 x9 o( S0 k: S- Y6 ?TRAINGD, Epoch 100/300, MSE 0.000435947/1e-05, Gradient 0.0161202/1e-10
) M4 a" W  x+ g7 g4 G1 iTRAINGD, Epoch 150/300, MSE 8.68462e-05/1e-05, Gradient 0.00769588/1e-10
TRAINGD, Epoch 200/300, MSE 1.45042e-05/1e-05, Gradient 0.00325667/1e-10
TRAINGD, Epoch 211/300, MSE 9.64816e-06/1e-05, Gradient 0.00266775/1e-10
# Y" r& S- V: T# L# n+ Y" mTRAINGD, Performance goal met.
; ^+ s' n$ s1 ^6 @5 J, d( }a = sim(net,p)

' l: q% B) t- E; s
plot(p,t,p,a,'o')
9 A4 A8 c" v, G, a& S8 Y
! E: t; C  @; M4 J: o
但是为什么老是报错：
' y3 [2 D/ C/ Q. K0 l??? Input argument "net" is undefined.