Classical Machine Learning

Separate the inner and outer groups

A journey through the kernel trick with Botie.

Classical Machine Learning · A journey with Botie

First visit? Learn the workshop controls

Botie's notebook

Could a Different View Make the Groups Easier to Separate?

Part 1 of 3

Imagine one group of points surrounded by another. Moving a straight dividing line around the picture will not separate them. We need to change the information used to describe each point, such as adding its distance from the middle.

Sources for this history

Boser, Guyon and Vapnik (1992), A Training Algorithm for Optimal Margin Classifiers

← Previous lesson: k-Means Clustering Read the full lesson and derivations