Machine Learning

, Volume 54, Issue 3, pp 187–193

Introduction to the Special Issue on Meta-Learning

  • Christophe Giraud-Carrier
  • Ricardo Vilalta
  • Pavel Brazdil

DOI: 10.1023/B:MACH.0000015878.60765.42

Cite this article as:
Giraud-Carrier, C., Vilalta, R. & Brazdil, P. Machine Learning (2004) 54: 187. doi:10.1023/B:MACH.0000015878.60765.42


Recent advances in meta-learning are providing the foundations to construct meta-learning assistants and task-adaptive learners. The goal of this special issue is to foster an interest in meta-learning by compiling representative work in the field. The contributions to this special issue provide strong insights into the construction of future meta-learning tools. In this introduction we present a common frame of reference to address work in meta-learning through the concept of meta-knowledge. We show how meta-learning can be simply defined as the process of exploiting knowledge about learning that enables us to understand and improve the performance of learning algorithms.

meta-learning meta-knowledge inductive bias dynamic bias selection 
Download to read the full article text

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Christophe Giraud-Carrier
    • 1
  • Ricardo Vilalta
    • 2
  • Pavel Brazdil
    • 3
  1. 1.ELCA Informatique SALausanneSwitzerland
  2. 2.Department of Computer ScienceUniversity of HoustonHoustonUSA
  3. 3.LIACC / Faculty of EconomicsUniversity of PortoPortoPortugal

Personalised recommendations