Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureHoofdstukAcademicpeer review

60 Downloads (Pure)


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.
Originele taal-2Engels
TitelAutomatic Machine Learning
SubtitelMethods, Systems, Challenges
RedacteurenFrank Hutter, Lars Kotthoff, Joaquin Vanschoren
Plaats van productieCham
Aantal pagina's27
ISBN van elektronische versie978-3-030-05318-5
ISBN van geprinte versie978-3-030-05317-8
StatusGepubliceerd - 2019


Duik in de onderzoeksthema's van 'Meta-learning'. Samen vormen ze een unieke vingerafdruk.

Citeer dit