Complexity in Analogy Tasks: An Analysis and Computational Model

  • Authors:

  • Philip Stahl;Marco Ragni

  • Affiliations:

  • University of Freiburg, email: philip.stahl@mars.uni-freiburg.de, ragni@cognition.uni-freiburg.de;University of Freiburg, email: philip.stahl@mars.uni-freiburg.de, ragni@cognition.uni-freiburg.de

  • Venue:
  • Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this article, we introduce a complexity measure for matrix tasks which occur in IQ-tests with respect to the kind of functions necessary to solve such tasks. The aim is to capture human reasoning difficulty. We implemented a program which is able to solve matrix tasks and to evaluate their complexity by our measure. The results of the evaluation are compared with the empirical difficulty ranking from Cattell's Culture Fair Test.