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

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

Vorschau
  • 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
Weitere Vorteile

Dieses Buch kaufen

eBook  
  • ISBN 978-3-030-05318-5
  • Dieses Buch ist ein Open Access Buch und ist frei zugänglich auf link.springer.com
Hardcover 53,49 €
Preis für Deutschland (Brutto)
  • ISBN 978-3-030-05317-8
  • Kostenfreier Versand für Individualkunden weltweit
  • Gewöhnlich versandfertig in 3-5 Werktagen.
Über dieses Buch

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. 

Inhaltsverzeichnis (11 Kapitel)

Inhaltsverzeichnis (11 Kapitel)
  • Hyperparameter Optimization

    Seiten 3-33

    Feurer, Matthias (et al.)

  • Meta-Learning

    Seiten 35-61

    Vanschoren, Joaquin

  • Neural Architecture Search

    Seiten 63-77

    Elsken, Thomas (et al.)

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

    Seiten 81-95

    Kotthoff, Lars (et al.)

  • Hyperopt-Sklearn

    Seiten 97-111

    Komer, Brent (et al.)

Dieses Buch kaufen

eBook  
  • ISBN 978-3-030-05318-5
  • Dieses Buch ist ein Open Access Buch und ist frei zugänglich auf link.springer.com
Hardcover 53,49 €
Preis für Deutschland (Brutto)
  • ISBN 978-3-030-05317-8
  • Kostenfreier Versand für Individualkunden weltweit
  • Gewöhnlich versandfertig in 3-5 Werktagen.
Loading...

Wir empfehlen

Loading...

Bibliografische Information

Bibliographic Information
Buchtitel
Automated Machine Learning
Buchuntertitel
Methods, Systems, Challenges
Herausgeber
  • Frank Hutter
  • Lars Kotthoff
  • Joaquin Vanschoren
Titel der Buchreihe
The Springer Series on Challenges in Machine Learning
Copyright
2019
Verlag
Springer International Publishing
Copyright Inhaber
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
Buchreihen ISSN
2520-131X
Auflage
1
Seitenzahl
XIV, 219
Anzahl der Bilder
9 schwarz-weiß Abbildungen, 45 Abbildungen in Farbe
Themen