Hi, I am kinda confused! I guess what's explained in the lecture is lambda (lambda=1/C) not C because in SVM error = (C* classification error) + distance error Which means high C penalizes classification error more heavily and therefore means less distance (less regularization) Here's the definition from sklearn.svm class: Cfloat, default=1.0 Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive. The penalty is a squared l2 penalty. Lemme know if I am wrong. Thank you.

Hi Ahmed, thahnks for reaching out and for the great question! You're absolutely right, you can look at the parameter as alpha, and I believe it's also how it's implemented in sk-learn. In the literature, you can sometimes find both variants, so it's important to make the distinction. Best, 365 Eli

Follow this topic

Ahmed Mady

Last answered:

14 Jun 2022

Posted on:

12 Jun 2022

Resolved: Do you mean C parameter as described in sklearn?

in Machine Learning with Support Vector Machines / Non-linearly separable classes - soft margin problem

1 answers ( 1 marked as helpful)

Elitsa Kaloyanova

Instructor

Posted on:

14 Jun 2022

Helpful answer

Resolved: Do you mean C parameter as described in sklearn?

Submit an answer