A hyperplane is an (n−1)-dimensional flat boundary in n-dimensional feature space. It divides that space into two regions, which a perceptron uses for its two class predictions. In two dimensions, the boundary is a line; in three, it is a plane. section 5.1
Sentence features
Represent a sentence by its word counts: with three words, a sentence containing them 5, 8, and 3 times is a point in three-dimensional space. A classifier’s plane divides such points into two regions. section 5.1
Figure 5.10 A dataset of sentences with three words is plotted in three dimensions. The classifier is represented by a plane that splits the space into two regions.
See how a plane divides a three-dimensional dataset of sentence points into two regions. section 5.1
