Machine learning paradigms

Abstract

In this chapter, we discuss the machine learning paradigm of Support Vector Machines which incorporates the principles of Empirical Risk Minimization and Structural Risk Minimization. SupportVector Machines constitute a state-of-theart classifier which is used as a benchmark algorithm to evaluate the classification accuracy of Artificial Immune System-based machine learning algorithms. In this chapter, we also present a special class of SupportVector Machines that are especially designed for the problem of One-Class Classification, namely the One-Class Support Vector Machines.