Support vector machine
Also: SVM, SVMs, support vector machines, support vector classifier
An SVM finds the hyperplane w·x + b = 0 that maximizes the margin 2/‖w‖ between classes; only the closest points, the support vectors, determine it. A soft-margin parameter C allows some violations, and kernels make it non-linear.
min ½‖w‖² + C Σ max(0, 1 − yᵢ(w·xᵢ + b))
Example
If training ends with ‖w‖ = 0.5, the margin between the two dashed lines is 2 / 0.5 = 4 units, and moving any point that is not a support vector leaves the boundary unchanged.