SVM is designed for two-class classification problem. If the data is not linear-separable, a kernel function is used. I want to know if there is exists any method that will indicate if the data is linearly separable or not.
$\begingroup$
$\endgroup$
1
-
$\begingroup$ I think perception Learning algorithm states that if data is linearly separable then the classifier will converge or find a decision boundary giving a 100% classification accuracy. So if you run a basic perception learning algorithm and it converges, data is linearly separable. $\endgroup$ – DuttaA Mar 27 '19 at 15:17
Add a comment
|
