StackedML
Practice
Labs
Questions
Models
Pricing
Sign in
Questions
/
Supervised Learning
/
Other Models
/
SVM (margin intuition, kernel trick)
← Previous
Next →
202.
Definition of Support Vectors
easy
What are support vectors in an SVM?
A
The feature vectors that span the directions of maximum variance in the training data
B
The training samples closest to the decision boundary that define and constrain the margin
C
The training samples that receive the highest weights during the optimization of the hinge loss
D
All training samples that are correctly classified by the decision boundary with nonzero confidence
Sign in to verify your answer
← Back to Questions