神经网络模式识别Matlab程序

神经网络模式识别 Matlab 程序识别加入 20%噪声的 A-Z 26 个字母。 (20%噪声情况下，完全能够识别)clear;close all;clc;[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;net.perFcn= 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);netn=net;netn.trainParam.goal=0.6;netn.trainParam.epochs=300;T=[targets targets targets targets];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);endnetn.trainParam.goal=0.1;netn.trainParam.epochs=500;netn.trainParam.show=5;P=alphabet;T=targets;[netn,tr]=train(netn,P,T);noise_percent=0.2;for k=1:26noisyChar=alphabet(:,k)+randn(35,1)*noise_percent;subplot(6,9,k+floor(k/9.5)*9);plotchar(noisyChar);de_noisyChar=sim(net,noisyChar);de_noisyChar=compet(de_noisyChar);answer=find(de_noisyChar==1);subplot(6,9,k+floor(k/9.5)*9+9);plotchar(alphabet(:,answer));endset(gcf, Position ,[10,60,900,700], color , w )运行结果如下：有噪声成功识别