The document discusses linear and non-linear support vector machine (SVM) algorithms. SVM finds the optimal hyperplane that separates classes with the maximum margin. For linear data, the hyperplane is a straight line, while for non-linear data it is a higher dimensional surface. The data points closest to the hyperplane that determine its position are called support vectors. Non-linear SVM handles non-linear separable data by projecting it into a higher dimension where it may become linearly separable.