Ensemble Methods: Foundations and Algorithms (Chapman & Hall/CRC Machine Learning & Pattern Recognition)

This book is good for new users and also for the expert users it is good for extend the work from this book.

As a business/data analyst and a machine learning PhD student, I found this book is a great read for people interested in ensemble methods from different perspectives - industrial and research. Prof. Zhou's book provides an in-depth review of robust ensemble techniques with both theoretical and empirical analysis. The reference section is also a great supplementary material for students and practitioners. As a researcher, I really enjoyed reading the "Diversity" and the "Ensemble pruning" chapters. As a data analyst, I found Ensemble Methods is also a great reference book for programmers who need to implement ensemble algorithms.

PROS: - nice coverCONS: - no gradient boosting machines (GBM) - no proofs - no state of art methods - only high level overview of some old methods - overpriced

This book provides a good survey on ensemble learning, and covers various interesting topics in ensemble learning. The references provided in this book are excellent. You can follow some related papers as suggested in the book to further investigate some topics. Since ensemble learning is very crucial to building practically useful model, I highly recommend this book to anyone who is interested in machine learning and data mining.

The author sorts out this complex field of ensemble learning in a very accessible way, which is possibly the most valuable point of this book in my opinion. I quite enjoy reading it.

The idea of ensemble learning is to construct a pool of learners and combine them in smart way into an overall system, rather than to construct a monolithic system. Ensemble learning has become a popular machine learning approach during the last years. The present monograph authored by Professor Zhi-Hua Zhou is a valuable contribution to theoretical and practical ensemble learning. The material is very well presented, preliminaries and basic knowledge is discussed in detail, many illustrations and pseudo-code tables help to understand the facts of this interesting field of research. Therefore the book will become a helpful tool for practitioners working in the field of machine learning or pattern recognition as well as for students of engineering or computer sciences at the graduate and postgraduate level. I heartily recommend the book!

Ensemble methods train multiple learners and then combine them for use. They have become a hot topic in academia since the 1990s, and are enjoying increased attention in industry. This is mainly based on their generalization ability, which is often much stronger than that of simple/base learners.It is always exciting to receive a new book written by a prominent researcher such as Professor Zhi-Hua Zhou. Discussion in the book starts from a strong theoretical foundation, but the author also includes many references to successful applications, which makes it a good book both for the researcher and the practitioner. Moreover, this book is not written from a single point of view, but rather includes the view from pattern recognition, data mining as well as (to a lesser extent) statistics.Important algorithms/approaches are discussed in pseudo-code, which facilitates the understanding. The author does not just provide the math, but also a clear explanation of the reasoning behind it. The discussion starts with the basic algorithm, and then lists a number of improvements that have been published in leading scientific journals.What I missed in this book? Some of the statistical methods (logistic regression), references to software and hybrid ensembles. This should be seen as suggestions for a second edition of the book.

I think this book is well-written,and Prof. Zhou is famous for his ensemble works. This book is very useful for researches to understanding the essence of ensemble learning.There are algorithms introductions and theoretical analysis in the book, and it is very comprehensive and state-of-the-art. There are many personal opinions in the book, they are insightful, as least for me. Thus, I sincerely recommend this book without reservation.

Ensemble methods train multiple learners and then combine them for use. They have become a hot topic in academia since the 1990s, and are enjoying increased attention in industry. This is mainly based on their generalization ability, which is often much stronger than that of simple/base learners.It is always exciting to receive a new book written by a prominent researcher such as Professor Zhi-Hua Zhou. Discussion in the book starts from a strong theoretical foundation, but the author also includes many references to successful applications, which makes it a good book both for the researcher and the practitioner. Moreover, this book is not written from a single point of view, but rather includes the view from pattern recognition, data mining as well as (to a lesser extent) statistics.Important algorithms/approaches are discussed in pseudo-code, which facilitates the understanding. The author does not just provide the math, but also a clear explanation of the reasoning behind it. The discussion starts with the basic algorithm, and then lists a number of improvements that have been published in leading scientific journals.What I missed in this book? Some of the statistical methods (logistic regression), references to software and hybrid ensembles. This should be seen as suggestions for a second edition of the book.