Introduction

Abstract

This book reviews the multiple instance learning paradigm. This concept was introduced as a type of supervised learning, dealing with datasets that are more complex than traditionally encountered and presented. Before formally describing multiple instance learning, its methods, developments and applications, this introductory chapter first recalls the general background of the knowledge discovery process in data collections. In Sect. 1.1, we describe the steps involved in this process and the traditional representation of data. Section 1.2 considers one particular knowledge discovery step, namely that of data preprocessing. We continue in Sect. 1.3 with a discussion on data mining methods that are applied on the preprocessed data in order to uncover some novel and useful information. Finally, Sect. 1.4 focuses on classification problems and their evaluation.