som.m

SOM神经网络

%P=[-3 -2 -2 0 0 0 0  2 2 3;0 1 -1 2 1 -1 -2 1 -1 0];
%样本准备
p11=mvnrnd([0.8,1.3],[0.5,0;0,0.4],20);p12=mvnrnd([0.3,1],[0.4,0;0,0.5],20);
%p13=mvnrnd([1.1,0.7],[0.4,0;0,0.5],6);
%训练样本准备
%输入矢量矩阵
%pp=[1 2 3;2 1 3;2 3 1;1 3 2;3 1 2;3 2 1];
pp=[p11' p12' ]';size(pp)
%输入数据化
%p=prestd(pp)';
P=pp';
a1=ones(20,1);a2=2*ones(20,1);
C=[a1' a2'];

T=ind2vec(C)

%plotvec(P,C);
title('dff');xlabel('ff');
ylabel('lP(2)');

net=newlvq(minmax(P),4,[.6 .4],0.1);

figure;
%plotvec(P,C);
hold on
W1=net.iw{1}
plot(W1(1,1),W1(1,2),'ow');
Title('jdk');
xlabel('IP(1)w(1)');
ylabel('lP(2) w(2)');
hold off
figure
%plotvec(P,C);
hold on
net.trainParam.epochs=150;
net.trainParam.show=Inf;
net=train(net,P,T);
plotvec(net.iw{1},vec2ind(net.lw{2}),'o');

p11=mvnrnd([0.8,1.3],[0.5,0;0,0.4],20);p12=mvnrnd([0.3,1],[0.4,0;0,0.5],20);
%p13=mvnrnd([1.1,0.7],[0.4,0;0,0.5],6);
%训练样本准备
%输入矢量矩阵
%pp=[1 2 3;2 1 3;2 3 1;1 3 2;3 1 2;3 2 1];
pp=[p11' p12' ]';size(pp)
%输入数据化
%p=prestd(pp)';
p=pp'

a=vec2ind(sim(net,p))