What do you think?
Rate this book
Automated Machine Learning: Methods, Systems, Challenges
This open access book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects descriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems. The recent success of commercial ML applications and the rapid growth of the field has created a high demand for off-the-shelf ML methods that can be used easily and without expert knowledge. However, many of the recent machine learning successes crucially rely on human experts, who manually select appropriate ML architectures (deep learning architectures or more traditional ML workflows) and their hyperparameters. To overcome this problem, the field of AutoML targets a progressive automation of machine learning, based on principles from optimization and machine learning itself. This book serves as a point of entry into this quickly-developing field for researchers and advanced students alike, as well as providing a reference for practitioners aiming to use AutoML in their work.
396 pages, Kindle Edition
Published May 17, 2019
304 people are currently reading
137 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 of 1 review
December 14, 2022
A great resource for a very academic but thorough look at the math, systems, and algorithms tackling the problem of AutoML.
It is essentially a collection of papers, which is both good and bad depending on the audience. For instance, if you are looking for a resource to show you how to implement AutoML in your business or to solve a particular problem, then look elsewhere. You will find no tutorials here.
However, if you are looking for an analysis of the various methods and ensembles out there with the full zeal of academic rigor, then start here.
I have implemented AutoML before reading this book to toy problems, but I never felt like I grasped what the different algorithms were doing (or how) until I read some of these chapters.
It will definitely be a resource I come back to again and again, if not for the content itself, then for the vast trove of references.
Recommended (to the right audience).
It is essentially a collection of papers, which is both good and bad depending on the audience. For instance, if you are looking for a resource to show you how to implement AutoML in your business or to solve a particular problem, then look elsewhere. You will find no tutorials here.
However, if you are looking for an analysis of the various methods and ensembles out there with the full zeal of academic rigor, then start here.
I have implemented AutoML before reading this book to toy problems, but I never felt like I grasped what the different algorithms were doing (or how) until I read some of these chapters.
It will definitely be a resource I come back to again and again, if not for the content itself, then for the vast trove of references.
Recommended (to the right audience).
Displaying 1 of 1 review