Terminology

We will now explore some of the terminology that goes into SVM classification:

• Hyperplane: Hyperplane is a decision boundary used to distinguish between two classes. Hyperplane dimensionality is decided by the number of features. It is also known as a decision plane.
• Support vectors: Support vectors are the closest points to the hyperplane and help in the orientation of the hyperplane by maximizing the margin.
• Margin: Margin is the maximum gap between the closest points. The larger the margin, the better the classification is considered. The margin can be calculated by the perpendicular distance from the support vector line.

The core objective of an SVM is to choose the hyperplane with the largest possible boundary between support vectors. The SVM finds the MMH in the following two stages:

1. Create hyperplanes that separate the data points in the best possible manner.
2. Select the hyperplane with maximum margin hyperplane:

The SVM algorithm is a faster and more...