Machine Learning

, Volume 54, Issue 3, pp 187-193

First online:

Introduction to the Special Issue on Meta-Learning

  • Christophe Giraud-CarrierAffiliated withELCA Informatique SA
  • , Ricardo VilaltaAffiliated withDepartment of Computer Science, University of Houston
  • , Pavel BrazdilAffiliated withLIACC / Faculty of Economics, University of Porto


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