I have a code for rbf neural network but i get error when processing
xdata=[12 25 1 5 ;8 9 21 03 ]
ydata-[2 6 9 8 ;2 8 7 4 ]
training=xdata(:,1:2);test=xdata(:,3:4);
samplesize=size(xdata);
for i=1:3
c=cvpartition(samplesize,'kfold',2)
trainInd=find(training(c,i));
testInd=find(test(c,i));
trainXMat=xdata(xdata(trainInd));
tstXMat=xdata((xdata(testInd)));
trainYMat=ydata(ydata(trainInd));
tstYMat=ydata((ydata(testInd)));
net1=newrbe(xdata,ydata,1.0);
end
is these correct,i get error as
Error using subsindex Function 'subsindex' is not defined for values of class 'cvpartition'.
Error in yasrbf (line 10) trainInd=find(training(c,i));
please help

 Akzeptierte Antwort

Walter Roberson
Walter Roberson am 7 Apr. 2012

0 Stimmen

cvpartition() creates a "cvpartition object", not a numeric value, but you are trying to use that object as an index in to the array training() .
Perhaps what you want is
trainInd = find(c.training(i));
or something like that.

4 Kommentare

kash
kash am 7 Apr. 2012
thanks walter it works but one thing is
CorrectRate: NaN
ErrorRate: NaN
i inculded
cp = classperf(groups);
cp = classperf(cp, tstYMat, testInd )
please help
Walter Roberson
Walter Roberson am 7 Apr. 2012
Sorry, that is outside my experience.
kash
kash am 7 Apr. 2012
ok walter thanks for ur suggestion
kash
kash am 7 Apr. 2012
another walter in another post
http://www.mathworks.in/matlabcentral/answers/34714-send-request-packet
ur code returns error
please help

Melden Sie sich an, um zu kommentieren.

Weitere Antworten (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by