ABSTRACT
In this chapter some examples of linear algebra applied to the field of data analytics and machine learning are given. Topics in the field of data analytics and machine learning were sought which applied linear algebra techniques and were easily within grasp without too much background development. Section 6.1 is a general introduction to the topics presented. Section 6.2 determines in what direction a data set is most spread. Section 6.3 presents the multi-use topic of principal component analysis. Section 6.4 introduces an integral technique in data analytics called dimen- sion reduction. A distance more statistically based is presented in Section 6.5 called Mahalanobis distance. A useful tool called data sphering is developed in Section 6.6. The remaining three sections deal with linear discriminant functions. In Section 6.7 the Fisher linear discriminant function is presented while the minimal square error linear discriminant function is presented in Section 6.9. The general notion of a linear discriminant function is discussed in Section 6.8.
