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：
. L4 g4 W1 O0 z' `' T0 pnet=newff([-1 2; 0 5],[3,1],{'tansig','purelin'},'traingd');
! @# @0 i* O8 ^, m: F7 L
8 z# t5 ]8 w" E% |" v6 L& O
6 [( i& o% N' `5 V5 A# ?net.trainParam.show = 50;
* w8 b  ?( e$ T- v* ^! s, Q& x% ynet.trainParam.lr = 0.05;
net.trainParam.epochs = 300;
net.trainParam.goal = 1e-5;
p = [-1 -1 2 2;0 5 0 5];
t = [-1 -1 1 1];

% _. [8 ~. I% p0 f3 L/ H
- q. Q- w( E) }) I4 nnet=train(net,p,t);
TRAINGD, Epoch 0/300, MSE 1.59423/1e-05, Gradient 2.76799/1e-10
( Q5 L4 d  q, E* G0 F
. v& F: [# J+ d5 u
TRAINGD, Epoch 50/300, MSE 0.00236382/1e-05, Gradient 0.0495292/1e-10
. F0 l1 A1 K( b  i! r6 p2 pTRAINGD, Epoch 100/300, MSE 0.000435947/1e-05, Gradient 0.0161202/1e-10
TRAINGD, Epoch 150/300, MSE 8.68462e-05/1e-05, Gradient 0.00769588/1e-10
4 g* [( V2 j0 z. X3 C  G6 n! ]4 VTRAINGD, Epoch 200/300, MSE 1.45042e-05/1e-05, Gradient 0.00325667/1e-10
7 \2 o# ]" S- L7 v$ O' TTRAINGD, Epoch 211/300, MSE 9.64816e-06/1e-05, Gradient 0.00266775/1e-10
TRAINGD, Performance goal met.
a = sim(net,p)
  s) w  y, B/ u, g; M/ ?
+ M/ d5 B2 r! J& _/ F# B, s
' X2 s2 g+ m8 r1 Y  _% P2 Cplot(p,t,p,a,'o')
5 l9 V. M" h: U; g# J, s: v0 j
2 X  ^; Y+ P$ l7 J6 N# I- l
: h$ [5 F) ~' x: s2 R" [! ^- u# I但是为什么老是报错：
??? Input argument "net" is undefined.