24小时热门版块排行榜

返回列表

aidexu2000

新虫 (初入文坛)

应助: 0 (幼儿园)
金币: 424
帖子: 11
在线: 43.1小时
虫号: 427209
注册: 2007-07-29
专业: 电力电子与电力传动

[求助] 高手帮忙看看啊，动态模糊神经网络的问题，谢谢！

程序如下：
clc
clear,close all
j(1:108)=[0 0 0 0 0 0 0 0 0 5 5 5 5 5 5 5 5 5 10 10 10 10 10 10 10 10 10 15 15 15 15 15 15 15 15 15 20 20 20 20 20 20 20 20 20 25 25 25 25 25 25 25 25 25 30 30 30 30 30 30 30 30 30 35 35 35 35 35 35 35 35 35 40 40 40 40 40 40 40 40 40 45 45 45 45 45 45 45 45 45 50 50 50 50 50 50 50 50 50 55 55 55 55 55 55 55 55 55]';
i(1:108)=[1.5 3.45 4.8 6.5 8.35 9.25 10.15 11.1 12.1 1.45 3.65 5.2 6.95 8.4 9.8 10.6 11.4 12.6 1.1 2.8 4.1 5.4 7.9 9.2 10.8 11.5 12.2 1.65 2.5 3.4 5.5 6.3 7.2 8.15 11 12.6 1 1.9 2.35 3.6 4.95 6.5 8.0 9.2 12.6 1.3 2.1 3.3 4.75 5.9 7.0 9.3 11 12.6 1.1 2.05 3.1 4.25 5.6 7.5 9 11 12.6 1.1 2.15 3.1 4.5 5.35 6.2 8.1 10 12.1 1.3 2.2 3.1 4.0 5.35 6.75 8 10 12.1 1.2 2.35 3.6 5.25 6.3 7.25 9.7 11 12.1 0.55 2.25 3.25 4.45 6.5 9.0 10.1 11.2 12.1 1.4 4.35 6.2 7.7 8.8 10 10.6 11 12.1]';
l(1:108)=[9.5 12 12.4 12.6 12.5 12.5 12.6 12.6 12.5 9.9 12.6 13.2 13.4 13.6 13.3 13.4 13.6 13.7 13.7 18.7 18.8 18.9 18.7 18.4 18.3 18.2 17.9 53.9 57.7 55.8 52.2 47.9 42.9 40.1 31.8 30.3 95.4 92 90.6 78.5 68 58.6 51.5 46.8 36.6 107.6 103 96.3 80.6 70 62.1 49.4 42.9 38.1 130.1 125.7 113.9 95.7 79.4 63.1 53.5 44.6 39.6 121.4 125 113.4 92.5 82.6 74 60.3 49.7 41.8 94.1 96.8 90.2 82.6 70.6 60.6 53.5 44.2 37.0 66.1 66.2 61.3 51.3 46.5 43.2 37.1 34.4 32.3 28.5 30.0 29.0 27.1 25.0 22.8 22.2 21.6 21.3 10.3 14.2 14.1 14.3 14.2 14.2 14.2 14.3 14.2]';
for k=1:108
p=[j(k);i(k)];
t=l(k);
end
%rand('seed',5);
%p=rand(1,200)*8-4;
%t=1.1*(1-p+2*p.^2).*exp(-p.^2./2);
[r,q]=size(p);[s2,q]=size(t);
kdmax=2;kdmin=0.2;gama=0.977;beta=0.9;width0=2;emax=1.1;
emin=0.02;k=1.1;kw=1.1;kerr=0.0015;
parameters(1)=kdmax;parameters(2)=kdmin;parameters(3)=gama;
parameters(4)=emax;parameters(5)=emin;parameters(6)=beta;
parameters(7)=width0;parameters(8)=k;parameters(9)=kw;
parameters(10)=kerr;
[w1,w2,width,rule,e,RMSE]=DFNN(p,t,parameters);
TA=RBF(dist(w1,p),1./width');
TA0=sum(TA);
[u,v]=size(w1);
TA1=TA./(ones(u,1)*TA0);
TA2=transf(TA1,p);
outTA2=w2*TA2;
figure,plot(rule,'r');
title('Fuzzy rule eneration');
xlabel('Input sample patterns');
ylabel('No of rules');
figure,plot(e,'r');
title('Actual output error');
xlabel('Input sample patterns');
figure,plot(RMSE,'r');
title('Root mean squared error (RMSE)');
xlabel('Input sample patterns');
figure,plot(p,t,'r+',p,outTA2,'bo');
title('Desired and actual outputs');
xlabel('Input data');
注释掉部分【%rand('seed',5);%p=rand(1,200)*8-4;%t=1.1*(1-p+2*p.^2).*exp(-p.^2./2);】换成注释上面的程序后，运行出现如下错误：
??? Output argument "e" (and maybe others) not assigned during call to "D:\Matlab\DNFN\TEST\DFNN.m (DFNN)".

Error in ==> DFNN at 27
if nargin<2

Error in ==> SRD at 22
[w1,w2,width,rule,e,RMSE]=DFNN(p,t,parameters);
本人是初学者，想用一组测试数据（两个输入，一个输出）建立模型，采用函数逼近的方法，但貌似不行。请高手指点：问题出在哪儿呢？谢谢！

回复此楼