CONTENTS 26.1 Introduction 563 26.2 Theoretical and Practical Reasons for Combining Classifiers 565 26.3 Taxonomies of Ensemble Methods 567 26.4 Nongenerative Ensembles 570

26.4.1 Ensemble Fusion Methods 570 26.4.2 Ensemble Selection Methods 572

26.5 Generative Ensembles 573 26.5.1 Resampling Methods 573 26.5.2 Feature Selection/Extraction Methods 575 26.5.3 Mixture of Experts 576 26.5.4 OC Methods 576 26.5.5 Randomized Ensemble Methods 577

26.6 Ensemble Methods in Astronomy and Astrophysics 578 26.7 Conclusions 582 Acknowledgments 582 References 582

26.1 INTRODUCTION Ensemble methods are statistical and computational learning procedures reminiscent of the human social learning behavior of seeking several opinions before making any crucial decision. The idea of combining the opinions of different “experts” to obtain an overall “ensemble” decision is rooted in our culture at least from the classical age of ancient Greece, and it has been formalized during the Enlightenment with the Condorcet Jury Theorem [45]), which proved that the judgment of a committee is superior to those of individuals, provided the individuals have reasonable competence.