A Fuzzy Model for Analogical Problem Solving
This work addresses the problem of modeling cognitive processes like analogical problem solving for researchers in psychology or AI, but it appears incremental as it builds on earlier stochastic models.
The authors tackled the modeling of analogical reasoning by developing a fuzzy model that represents steps as fuzzy subsets and uses the Shannon-Wiener diversity index to measure abilities, comparing it with a stochastic model and presenting a classroom experiment.
In this paper we develop a fuzzy model for the description of the process of Analogical Reasoning by representing its main steps as fuzzy subsets of a set of linguistic labels characterizing the individuals' performance in each step and we use the Shannon- Wiener diversity index as a measure of the individuals' abilities in analogical problem solving. This model is compared with a stochastic model presented in author's earlier papers by introducing a finite Markov chain on the steps of the process of Analogical Reasoning. A classroom experiment is also presented to illustrate the use of our results in practice.