example4_10.m

基于matlab的网络设计利用神经网络进行分类识别

%网络初始化
[alphabet,targets]=prprob;
[R,Q]=size(alphabet);
[S2,Q]=size(targets);
S1=10;
P=alphabet;
net= newff(minmax(P),[S1 S2],{'logsig' 'logsig'},'traingdx');
net.LW{2,1}=net.LW{2,1}*0.01;
net.b{2}=net.b{2}*0.01;


T=targets;
%网络训练参数设置
net.performFcn='sse';
net.trainParam.goal=0.1;
net.trainParam.show=20;
net.trainParam.epochs=5000;
net.trainParam.mc=0.95;
%开始对无误差输入向量进行训练
[net,tr]=train(net,P,T);
%网络训练参数设置,并对有误差输入向量进行训练
netn=net;
netn.trainParam.goal=0.6;
netn.trainParam.epochs=300;
T=[targets targets targets targets];
pause
for pass=1:10
P=[alphabet,alphabet,...
(alphabet+randn(R,Q)*0.1),...
(alphabet+randn(R,Q)*0.2)];
[netn,tr]=train(netn,P,T);
pause
end
%网络再次对无误差输入向量进行训练
P=alphabet;
T=targets;
net.performFcn='sse';
net.trainParam.goal=0.1;
net.trainParam.show=20;
net.trainParam.epochs=5000;
net.trainParam.mc=0.95;
[net,tr]=train(net,P,T);
pause
%测试网络的容错性
noise_range=0:0.05:0.5;
max_test=100;
T=targets;
for i=1:11
  noiselevel(i)=noise_range(i);
  errors1(i)=0;
  errors2(i)=0;
  for j=1:max_test
    P=alphabet+randn(35,26)*noiselevel(i);
    % 测试未经误差训练的网络 
    A=sim(net,P);


    AA=compet(A);
    errors1(i)=errors1(i)+sum(sum(abs(AA-T)))/2;
    % 测试经过误差训练的网络
    An=sim(netn,P);
    AAn=compet(An);
    errors2(i)=errors2(i)+sum(sum(abs(AAn-T)))/2;
   end
end
pause
figure
plot(noise_range,errors1*100,'--',noise_range,errors2*100);
title('识别错误率');
xlabel('噪声指标');
ylabel('未经误差训练的网络 - -   经过误差训练的网络---');
%对实际含噪声的字母进行识别
for index=1:5:26
noisyJ=alphabet(:,index)+randn(35,1)*0.2;
figure;
plotchar(noisyJ);
A2=sim(net,noisyJ);
A2=compet(A2);
answer=find(compet(A2)==1);
figure;
plotchar(alphabet(:,answer));
end