Kernel SVMs
Bộ phân loại tuyến tính với Python
Michael (Mike) Gelbart
Instructor, The University of British Columbia
Transforming your features
Transforming your features
Transforming your features
$\textrm{transformed feature} =$
$ (\textrm{original feature})^2$
Transforming your features
$\textrm{transformed feature} =$
$ (\textrm{original feature})^2$
Transforming your features
$\textrm{transformed feature} =$
$ (\textrm{original feature})^2$
Kernel SVMs
from sklearn.svm import SVC
svm = SVC(gamma=1) # default is kernel="rbf"
Kernel SVMs
from sklearn.svm import SVC
svm = SVC(gamma=0.01) # default is kernel="rbf"
- smaller
gammaleads to smoother boundaries
Kernel SVMs
from sklearn.svm import SVC
svm = SVC(gamma=2) # default is kernel="rbf"
- larger
gammaleads to more complex boundaries
