sklearn.svm.SVC is based on libsvm so no need to compare the two.
sklearn.svm.LinearSVC is based on liblinear.

In theory, SVMs do what SVMs do: maximize a classification margin given
some tolerance for wrong classifications. Apart from numerical errors in
optimization, I don't see how accuracy scores can be different if the
algorithm has converged (with stress on that last word). The numerical
errors incurred shouldn't ever change a prediction that drastically.

On Tue, Mar 3, 2015 at 9:53 PM, Pagliari, Roberto <rpagli...@appcomsci.com>
wrote:

> Has anybody ever compared Matlab SVM vs sklearn or libsvm?
>
>
>
> It’d be interested to know about the difference in accuracy between them
> (using the same dataset and similar settings).
>
>
>
> Thank you,
>
>
>
>
> ------------------------------------------------------------------------------
> Dive into the World of Parallel Programming The Go Parallel Website,
> sponsored
> by Intel and developed in partnership with Slashdot Media, is your hub for
> all
> things parallel software development, from weekly thought leadership blogs
> to
> news, videos, case studies, tutorials and more. Take a look and join the
> conversation now. http://goparallel.sourceforge.net/
> _______________________________________________
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
>
------------------------------------------------------------------------------
Dive into the World of Parallel Programming The Go Parallel Website, sponsored
by Intel and developed in partnership with Slashdot Media, is your hub for all
things parallel software development, from weekly thought leadership blogs to
news, videos, case studies, tutorials and more. Take a look and join the 
conversation now. http://goparallel.sourceforge.net/
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to