Machine Learning

Abstract

The purpose of this chapter is to present fundamental ideas and techniques of machine learning suitable for the field of this book, i.e., for automated scientific discovery. The chapter focuses on those symbolic machine learning methods, which produce results that are suitable to be interpreted and understood by humans. This is particularly important in the context of automated scientific discovery as the scientific theories to be produced by machines are usually meant to be interpreted by humans. This chapter contains some of the most influential ideas and concepts in machine learning research to give the reader a basic insight into the field. After the introduction in Sect. 1, general ideas of how learning problems can be framed are given in Sect. 2. The section provides useful perspectives to better understand what learning algorithms actually do. Section 3 presents the Version space model which is an early learning algorithm as well as a conceptual framework, that provides important insight into the general mechanisms behind most learning algorithms. In section 4, a family of learning algorithms, the AQ family for learning classification rules is presented. The AQ family belongs to the early approaches in machine learning. The next, Sect. 5 presents the basic principles of decision tree learners. Decision tree learners belong to the most influential class of inductive learning algorithms today. Finally, a more recent group of learning systems are presented in Sect. 6, which learn relational concepts within the framework of logic programming. This is a particularly interesting group of learning systems since the framework allows also to incorporate background knowledge which may assist in generalisation. Section 7 discusses Association Rules – a technique that comes from the related field of Data mining. Section 8 presents the basic idea of the Naive Bayesian Classifier. While this is a very popular learning technique, the learning result is not well suited for human comprehension as it is essentially a large collection of probability values. In Sect. 9, we present a generic method for improving accuracy of a given learner by generatingmultiple classifiers using variations of the training data. While this works well in most cases, the resulting classifiers have significantly increased complexity and, hence, tend to destroy the human readability of the learning result that a single learner may produce. Section 10 contains a summary, mentions briefly other techniques not discussed in this chapter and presents outlook on the potential of machine learning in the future.