In this chapter, we will be covering both support vector machines and neural networks, which are on the higher side of computational complexity and require relatively significant resources for calculations, but do provide significantly better results compared with other machine learning methods in most cases.
A support vector machine (SVM) can be imagined as a surface that maximizes the boundaries between various types of points of data that is represent in multidimensional space, also known as a hyperplane, which creates the most homogeneous points in each subregion.
Support vector machines can be used on any type of data, but have special extra advantages for data types with very high dimensions relative to the observations, for example:
- Text classification, in which language has the very dimensions of word vectors
- For the quality control of DNA sequencing by labeling chromatograms correctly