Does matlab optimizes SVM linear parameters automatically

Question

I am using SVM in Matlab for classification. I directly gave the training data set and class labels for training but without any parameters. My code looks like this:

traningData = myData;
label = [1 1 0 0 0 0 0 0 1 1 1 1 0 1 1 0 1 1 1 0];
SVMStructure = svmtrain (myData, label);
... %further prediction part

I found the default SVM method is 'linear', so here in my code, it should be 'linear' then. But how about the parameter C? It says from the Matlab documentation:

The resulting structure, SVMstruct, contains the optimized parameters from the SVM algorithm, enabling you to classify new data

So does that mean Matlab automatically optimizes the paramter C for linear SVM here?

Marc Claesen · Accepted Answer · 2013-07-05 13:38:29Z

0

Those built in routines are pretty awful. They allow no flexibility and use dinosaur solvers. It is quite unclear what is going on behind the scenes.

I strongly recommend using another library for SVM training. Many popular packages are free and have MATLAB interfaces.

answered Jul 5, 2013 at 13:38

Marc Claesen

17.1k6 gold badges30 silver badges62 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Does matlab optimizes SVM linear parameters automatically

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related