Why do SVMs use kernels?
mediumAnswer
- Kernels let SVMs learn nonlinear boundaries without explicitly computing high-dimensional features — the kernel trick evaluates inner products in an implicit feature space.
- Common kernels: linear (baseline), polynomial, RBF (default nonlinear choice), sigmoid.
- RBF works well when the boundary is smooth but nonlinear; tune C and gamma.
Check yourself — multiple choice
- Kernels make training faster on huge datasets
- Kernels enable nonlinear boundaries via implicit feature maps
- Kernels replace regularization
- Kernels are needed only for regression
Kernels compute inner products in a higher-dimensional space implicitly (the kernel trick).
#svm#kernels
Practise Supervised Learning
215 interview questions in this topic.