.png)
SVM Hyperplane
In Support Vector Machine, a hyperplane is the decision boundary that separates data points belonging to different classes.
What is a Hyperplane
# In 2D, a hyperplane is a line: w1*x1 + w2*x2 + b = 0
# In 3D, a hyperplane is a plane: w1*x1 + w2*x2 + w3*x3 + b = 0
# In n dimensions, it generalizes to an (n-1)-dimensional flat surfaceClassifying with the Hyperplane
Once the hyperplane is defined, a new data point is classified based on which side of it the point falls - points on one side belong to one class, and points on the other side belong to the other class.
Visualizing in 2D
For a simple two-feature dataset, the hyperplane is just a straight line drawn so that it separates the two groups of points as cleanly as possible, with as much space as possible on either side.
There can be infinitely many hyperplanes that separate two classes - SVM's job is to find the single best one, which is covered next.
Coming Up Next
Next, you'll learn about the Maximum Margin Hyperplane and why it's the one SVM chooses.