Case 5 – solving linearly non-separable problems

The hyperplanes we have found up till now are linear, for instance, a line in a two-dimensional feature space, or a surface in a three-dimensional one. However, in the following example, we are not able to find any linear hyperplane that can separate two classes:

Intuitively, we observe that data points from one class are closer to the origin than those from another class. The distance to the origin provides distinguishable information. So we add a new feature, , and transform the original two-dimensional ...

Get Python Machine Learning By Example - Second Edition now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.