Meta-learning

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

31 Downloads (Pure)

Abstract

Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible. Not only does this dramatically speed up and improve the design of machine learning pipelines or neural architectures, it also allows us to replace hand-engineered algorithms with novel approaches learned in a data-driven way. In this chapter, we provide an overview of the state of the art in this fascinating and continuously evolving field.
Original languageEnglish
Title of host publicationAutomatic Machine Learning
Subtitle of host publicationMethods, Systems, Challenges
EditorsFrank Hutter, Lars Kotthoff, Joaquin Vanschoren
Place of PublicationCham
PublisherSpringer
Chapter2
Pages39-61
Number of pages27
ISBN (Electronic)978-3-030-05318-5
ISBN (Print)978-3-030-05317-8
DOIs
Publication statusPublished - 2019

Keywords

  • meta-learning
  • Automatic Machine Learning

Fingerprint Dive into the research topics of 'Meta-learning'. Together they form a unique fingerprint.

  • Cite this

    Vanschoren, J. (2019). Meta-learning. In F. Hutter, L. Kotthoff, & J. Vanschoren (Eds.), Automatic Machine Learning: Methods, Systems, Challenges (pp. 39-61). Springer. https://doi.org/10.1007/978-3-030-05318-5_2