24小时热门版块排行榜

返回列表

westlifexp

铜虫 (小有名气)

应助: 1 (幼儿园)
金币: 72.9
散金: 3
帖子: 82
在线: 43.8小时
虫号: 1450881
注册: 2011-10-19
性别: GG
专业: 塑料

[求助] BP神经网络预测代码出现问题

小弟，使用BP神经网络进行预测，以下是代码，麻烦帮忙看看：
%  定义训练样本
% P 为输入矢量
P=[0.007,0.003,0.063,0.032,0.003;0.338,0.003,0.375,0.677,0.668;0.669,0.003,0.688,0.677,0.668;0.669,0.003,0.688,0.677,0.668;1,1,0.063,0.677,0.668];
% T 为目标矢量
T=[0.106,0.498,0.95;0.066,0.05,0.05;0.05,0.95,0.513;0.95,0.94,0.907];
%  创建一个新的前向神经网络
net=newff(minmax(P),[10,3],{'tansig','purelin'},'traingdm')
%  当前输入层权值和阈值
inputWeights=net.IW{1,1}；
inputbias=net.b{1}；
%  当前网络层权值和阈值
layerWeights=net.LW{2,1}；
layerbias=net.b{2}；
%  设置训练参数
net.trainParam.show = 50;
net.trainParam.lr = 0.001;
net.trainParam.mc = 0.9;
net.trainParam.epochs = 2000;
net.trainParam.goal = 1e-5;
%  调用 TRAINGDM 算法训练 BP 网络
net=train(net,P,T);
%  对 BP 网络进行仿真
A = sim(net,P)；
%  计算仿真误差
E = T - A；
MSE=mse(E)；
figure，
plot((1:5),T,'-*',(1:5),A,'-o')；

错误如下：
??? net.trainParam.lr = 0.001; 学习速率
                           |
Error: Missing variable or function.

360截图20121225205218893.jpg

[ Last edited by westlifexp on 2012-12-26 at 18:26 ]

回复此楼