AIExplainer
Mathematics Advanced 2 min read

What is hyperplane?

A high-dimensional space that separates data into different categories

Pronunciation: hy-per-playn

In machine learning, a hyperplane is a boundary that divides a high-dimensional space into different regions. It's used to classify data points into different categories, such as 0 and 1, or yes and no.

Imagine a piece of paper that separates two rooms in a house. The paper is like a hyperplane, dividing the space into two distinct areas. Just as the paper can be oriented in different ways to separate the rooms, a hyperplane can be oriented in different ways to separate data points into different categories.

A hyperplane can be used to classify images of animals as either 'cats' or 'dogs'. The hyperplane would separate the high-dimensional space of image features, such as pixel values and textures, into two regions, one for cats and one for dogs.

Hyperplanes are used in machine learning algorithms, such as support vector machines, to classify data and make predictions. They're especially useful when dealing with high-dimensional data, where it's hard to visualize the relationships between data points.

Some people think that a hyperplane is a physical space, but it's actually a mathematical concept that exists in a high-dimensional space. Others think that hyperplanes are only used in machine learning, but they're also used in other fields, such as physics and engineering.

The concept of hyperplanes has been around for centuries, dating back to the work of mathematicians such as Euclid and Descartes. However, the use of hyperplanes in machine learning is a more recent development, dating back to the 1990s.

decision boundary separating boundary classification boundary

Three products for different needs — explore what’s relevant to you.