MATLAB: Cost function in classification learner app

classification learner appcostfunctionsvm

How is it possible to use a costfunction/ penalty function for a Support Vector Machine in the classification Learner App?

If it is not possible, is there a way to train a SVM manually for more than 2 classes?

Best Answer

Hi,

a cost function is not available as far as i know. For more than two classes you could use the function

fitcecoc

see documentation here:

https://de.mathworks.com/help/stats/fitcecoc.html?searchHighlight=fitcecoc&s_tid=doc_srchtitle

Best regards

Stephan

Related Solutions

MATLAB: Where is Naive Bayes in classification learner

Hi Zeynab,

After importing the data to be trained Naive Bayes Classifier can be found by clicking on the down arrow button right of the Fine Tree button option. See the attached images.

MATLAB: How to give inputs to classifier

If you have extracted the trained SVM from the Classification Learner app this is how you do it:

%you trained it to predict - let's say - images:
trainedClassifier = trainedModel.ClassificationSVM;  %You export the trainedModel struct from the app.
[imagepred] = predict(trainedClassifier,imagefeatures);
%imagepred - output data (usually 'categorical' type) for more information look up the predict function.

If this is not your problem please try to specify more details :)

Best Answer

Related Solutions

MATLAB: Where is Naive Bayes in classification learner

MATLAB: How to give inputs to classifier

Related Question