15 SVMs and machine learning on docs

Question 1

Margin

Answer 1

The distance from the decision surface to the closest data point determines the margin of the classifier.

Question 2

Support vectors

Answer 2

The points that are closest to the decision boundary. 40

Question 3

Kernel trick

Answer 3

SVMs provide an easy and efficient way of doing a mapping to higher di- mensional space, which is referred to as the kernel trick.