Building a framework to design and evaluate meta-learning support systems

  • Authors:

  • Kazuhisa Seta;Minoru Fujiwara;Daijiro Noguchi;Hiroshi Maeno;Mitsuru Ikeda

  • Affiliations:

  • Osaka Prefecture University, Department of Mathematics and Information Sciences, Skai, Osaka, Japan;Osaka Prefecture University, Department of Mathematics and Information Sciences, Skai, Osaka, Japan;Osaka Prefecture University, Department of Mathematics and Information Sciences, Skai, Osaka, Japan;Osaka Prefecture University, Department of Mathematics and Information Sciences, Skai, Osaka, Japan;JAIST, Nomi, Ishikawa, Japan

  • Venue:
  • KES'10 Proceedings of the 14th international conference on Knowledge-based and intelligent information and engineering systems: Part IV
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

It is difficult to generalize and accumulate experiences of system development as methodologies for building meta-learning support systems. Therefore, we need to build a framework that is useful to design and evaluate meta-learning support systems. Thus we propose a framework as a basis to design and evaluate meta-learning support systems. In this paper, we firstly describe our philosophy to solve the problem. Secondly, we propose a metalearning process model as a basis to understand meta-learning task and what kinds of factors of difficulty exist in performing meta-learning activities. Thirdly, we explain our conceptualization as a basis to design support functions for prompting meta-learning processes. Then, we integrate a meta-learning process model and the conceptualizations, so that we can design and evaluate meta-learning systems. Finally, we illustrate the usefulness of the framework by taking our presentation based meta-learning system as an example.