Skip to content
Sign in

What is Support Vector Machine?

Also known as: SVM

A Support Vector Machine (SVM) is a supervised machine learning algorithm mainly used for classification (and sometimes regression). It finds the optimal boundary, called a hyperplane, that separates data points of different classes with the maximum margin.

SVM works by identifying the hyperplane that best divides the classes in the feature space. The goal is to maximize the distance (margin) between the hyperplane and the nearest data points from each class, known as support vectors.

For data that is not linearly separable, SVM uses the kernel trick to map inputs into higher-dimensional spaces where a separating hyperplane can be found. Common kernels include linear, polynomial, and radial basis function (RBF).

Training involves solving an optimization problem that balances maximizing the margin while minimizing classification errors, often using techniques like soft margins for noisy data.

Example

Imagine sorting apples and oranges based on weight and color. An SVM would plot the fruits and draw the widest possible line separating the two groups, using only the apples and oranges closest to that line (the support vectors) to define it.

Why it matters

SVMs remain relevant for high-dimensional data tasks like text classification and bioinformatics due to their effectiveness with smaller datasets and strong theoretical foundations. They also influenced later kernel-based methods in modern AI.

Frequently asked questions

Support vectors are the data points closest to the decision boundary; they alone determine the position and orientation of the separating hyperplane.