Thanks! For testing purposes this rescaling works! But unfortunately due to
timing constraints I'm not able to do the rescaling of the data, so as I
mentioned I have to work on with unscaled data. So I have to calculate
$f(\vec x) = sum_{i \in sv} coefs_i \langle \vec x_i \cdot \vec x \rangle -
\rho$, where the sum runs over the support vectors (sorry, no LaTex
available here ). The problem is how to get unscaled coefs and rho to
calculate the result of the formula in order to save calculation time for
the evaluation of the formula.
Greetings
Matthias
--
View this message in context:
http://r.789695.n4.nabble.com/Scaling-in-SVM-tp3664588p3666945.html
Sent from the R help mailing list archive at Nabble.com.
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
