The Springer Series on Challenges in Machine Learning
Open Access This content is freely available online to anyone, anywhere at any time.

Automated Machine Learning

Methods, Systems, Challenges

Editors: Hutter, Frank, Kotthoff, Lars, Vanschoren, Joaquin (Eds.)

Free Preview
  • Presents a tutorial-level overview of the methods underlying automatic machine learning, enabling readers to easily understand the key concepts behind AutoML
  • Offers a comprehensive collection of in-depth descriptions of AutoML systems, allowing readers to see how the key concepts have been implemented in the context of actual systems
  • Discusses an independent international competition of many different systems, providing an independent evaluation of pros and cons of different AutoML approaches
see more benefits

Buy this book

eBook  
  • ISBN 978-3-030-05318-5
  • This book is an open access book, you can download it for free on link.springer.com
Hardcover 51,99 €
price for Spain (gross)
  • ISBN 978-3-030-05317-8
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
  • The final prices may differ from the prices shown due to specifics of VAT rules
About this book

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. 

Table of contents (11 chapters)

Table of contents (11 chapters)
  • Hyperparameter Optimization

    Pages 3-33

    Feurer, Matthias (et al.)

  • Meta-Learning

    Pages 35-61

    Vanschoren, Joaquin

  • Neural Architecture Search

    Pages 63-77

    Elsken, Thomas (et al.)

  • Auto-WEKA: Automatic Model Selection and Hyperparameter Optimization in WEKA

    Pages 81-95

    Kotthoff, Lars (et al.)

  • Hyperopt-Sklearn

    Pages 97-111

    Komer, Brent (et al.)

Buy this book

eBook  
  • ISBN 978-3-030-05318-5
  • This book is an open access book, you can download it for free on link.springer.com
Hardcover 51,99 €
price for Spain (gross)
  • ISBN 978-3-030-05317-8
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
  • The final prices may differ from the prices shown due to specifics of VAT rules
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Automated Machine Learning
Book Subtitle
Methods, Systems, Challenges
Editors
  • Frank Hutter
  • Lars Kotthoff
  • Joaquin Vanschoren
Series Title
The Springer Series on Challenges in Machine Learning
Copyright
2019
Publisher
Springer International Publishing
Copyright Holder
The Editor(s) (if applicable) and The Author(s)
eBook ISBN
978-3-030-05318-5
DOI
10.1007/978-3-030-05318-5
Hardcover ISBN
978-3-030-05317-8
Series ISSN
2520-131X
Edition Number
1
Number of Pages
XIV, 219
Number of Illustrations
9 b/w illustrations, 45 illustrations in colour
Topics